llama-cpp-python
llama-cpp-python copied to clipboard
abetlen
llama-cpp-python not using GPU on m1
Prerequisites
Please answer the following questions for yourself before submitting an issue.
- [x] I am running the latest code. Development is very rapid so there are no tagged versions as of now.
- [x] I carefully followed the README.md.
- [x] I searched using keywords relevant to my issue to make sure that I am creating a new issue that is not already open (or closed).
- [x] I reviewed the Discussions, and have a new bug or useful enhancement to share.
Expected Behavior
I am using llama-cpp-python on M1 mac . I installed using the cmake flag as mentioned in README.
I am able to run inference, but I am noticing that its mostly using CPU .
I expected it to use GPU
How do I make sure llama-cpp-python is using GPU on m1 mac?
Current Behavior
I am using llama-cpp-python on M1 mac . I installed using the cmake flag as mentioned in README.
I am able to run inference, but I am noticing that its mostly using CPU .
Environment and Context
Please provide detailed information about your computer setup. This is important in case the issue is not reproducible except for under certain specific conditions.
M1 Mac
llama_cpp_python 0.2.6
Python 3.9.0
macOS 13.5.2
Steps to Reproduce
Please provide detailed steps for reproducing the issue. We are not sitting in front of your screen, so the more detail the better.
- Load llama2-7b 4-bit quantization model
- Run inference
Hi @abetlen I am from TorchServe and working on showing an example with llama-cpp-python. I would appreciate your assistance with this
I use llama-cpp-python with LangChain on M1 and just reinstalled llama-cpp-python with Metal support, following the instructions here and using the command below:
CMAKE_ARGS="-DLLAMA_METAL=on" FORCE_CMAKE=1 pip install --upgrade --force-reinstall llama-cpp-python --no-cache-dir
But when running the llama2 inference on a notebook, I don't see any GPU Time in the Activity Monitor - not sure if this is one right way to monitor the GPU usage:
Will try llama.cpp to see if the inference there shows any GPU time and to hopefully narrow down the cause..
@agunapal
Yes running the llama.cpp's main shows GPU Time:
Looks like it's something related to llama_cpp_python - btw, the CMAKE_ARGS="-DLLAMA_METAL=on" FORCE_CMAKE=1 pip install command above installed the version 0.2.7 of llama-cpp-python.
Hi @agunapal sorry to get to this so late, are you setting the n_gpu_layers parameter? This is required to offload layers to the gpu and is off by default.
Hi @abetlen Thanks for getting back.
Is there a guide on whats supported on M1
I get errors when I set n_gpu_layers to -1
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1 Pro
ggml_metal_init: picking default device: Apple M1 Pro
ggml_metal_init: loading '/Users/agunapal/opt/anaconda3/envs/llama-cpp/lib/python3.9/site-packages/llama_cpp/ggml-metal.metal'
ggml_metal_init: error: Error Domain=MTLLibraryErrorDomain Code=3 "program_source:41:9: error: invalid type 'const constant int64_t &' (aka 'const constant long &') for buffer declaration
constant int64_t & nb,
^~~~~~~~~~~~~~~~~~~~~~~~
program_source:41:21: note: type 'int64_t' (aka 'long') cannot be used in buffer pointee type
constant int64_t & nb,
^
program_source:60:9: error: invalid type 'const constant int64_t &' (aka 'const constant long &') for buffer declaration
constant int64_t & nb,
^~~~~~~~~~~~~~~~~~~~~~~~
program_source:60:21: note: type 'int64_t' (aka 'long') cannot be used in buffer pointee type
constant int64_t & nb,
^
program_source:107:9: error: invalid type 'const constant int64_t &' (aka 'const constant long &') for buffer declaration
constant int64_t & ne00,
^~~~~~~~~~~~~~~~~~~~~~~~~
program_source:107:20: note: type 'int64_t' (aka 'long') cannot be used in buffer pointee type
FYI, here is the integrated example https://github.com/pytorch/serve/tree/master/examples/LLM/llama2/chat_app
It will be great if we can get this to use the GPU
@agunapal thanks for providing that. It looks like the issue might actually be with llama.cpp / your version of metal as it's only happening when the metal kernel file is loaded (ggml-metal.metal).
Do you mind testing using llama.cpp with the ./main program, if you get the same error you should report the issue there. If you could also kindly link back to the issue here I can update this library as soon as it's fixed.
@abetlen llama-cpp works for me
Do you thinking building llama-cpp-python from source would help.
llama_print_timings: load time = 1340.59 ms
llama_print_timings: sample time = 493.30 ms / 670 runs ( 0.74 ms per token, 1358.21 tokens per second)
llama_print_timings: prompt eval time = 1121.16 ms / 257 tokens ( 4.36 ms per token, 229.23 tokens per second)
llama_print_timings: eval time = 20353.33 ms / 669 runs ( 30.42 ms per token, 32.87 tokens per second)
llama_print_timings: total time = 22316.10 ms
ggml_metal_free: deallocating
Log end
@agunapal yeah that's very strange, can you post the top part of the ./main command where it's setting up?
You can also build llama.cpp as a shared library with cmake -DBUILD_SHARED_LIBS .. in the llama.cpp/build folder and copy the shared library and .metal file to the llama_cpp folder in your site packages.
Additionally running otool -L <shared-library/executable> would tell us if llama.cpp ./main and the llama-cpp-python shared library are linked against the same metal system libraries (not sure why they wouldn't be).
@abetlen Here it is
Log start
main: build = 1250 (b541b4f)
main: built with Apple clang version 14.0.3 (clang-1403.0.22.14.1) for arm64-apple-darwin22.6.0
main: seed = 1696111389
llama_model_loader: loaded meta data with 19 key-value pairs and 291 tensors from /Users/agunapal/Documents/experiments/llama/ggml-model-q4_0.gguf (version GGUF V2 (latest))
llama_model_loader: - tensor 0: token_embd.weight q4_0 [ 4096, 32000, 1, 1 ]
llama_model_loader: - tensor 1: blk.0.attn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 2: blk.0.ffn_down.weight q4_0 [ 11008, 4096, 1, 1 ]
llama_model_loader: - tensor 3: blk.0.ffn_gate.weight q4_0 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 4: blk.0.ffn_up.weight q4_0 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 5: blk.0.ffn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 6: blk.0.attn_k.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 7: blk.0.attn_output.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 8: blk.0.attn_q.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 9: blk.0.attn_v.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 10: blk.1.attn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 11: blk.1.ffn_down.weight q4_0 [ 11008, 4096, 1, 1 ]
llama_model_loader: - tensor 12: blk.1.ffn_gate.weight q4_0 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 13: blk.1.ffn_up.weight q4_0 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 14: blk.1.ffn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 15: blk.1.attn_k.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 16: blk.1.attn_output.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 17: blk.1.attn_q.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 18: blk.1.attn_v.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 19: blk.10.attn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 20: blk.10.ffn_down.weight q4_0 [ 11008, 4096, 1, 1 ]
llama_model_loader: - tensor 21: blk.10.ffn_gate.weight q4_0 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 22: blk.10.ffn_up.weight q4_0 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 23: blk.10.ffn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 24: blk.10.attn_k.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 25: blk.10.attn_output.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 26: blk.10.attn_q.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 27: blk.10.attn_v.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 28: blk.11.attn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 29: blk.11.ffn_down.weight q4_0 [ 11008, 4096, 1, 1 ]
llama_model_loader: - tensor 30: blk.11.ffn_gate.weight q4_0 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 31: blk.11.ffn_up.weight q4_0 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 32: blk.11.ffn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 33: blk.11.attn_k.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 34: blk.11.attn_output.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 35: blk.11.attn_q.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 36: blk.11.attn_v.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 37: blk.12.attn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 38: blk.12.ffn_down.weight q4_0 [ 11008, 4096, 1, 1 ]
llama_model_loader: - tensor 39: blk.12.ffn_gate.weight q4_0 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 40: blk.12.ffn_up.weight q4_0 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 41: blk.12.ffn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 42: blk.12.attn_k.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 43: blk.12.attn_output.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 44: blk.12.attn_q.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 45: blk.12.attn_v.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 46: blk.13.attn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 47: blk.13.ffn_down.weight q4_0 [ 11008, 4096, 1, 1 ]
llama_model_loader: - tensor 48: blk.13.ffn_gate.weight q4_0 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 49: blk.13.ffn_up.weight q4_0 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 50: blk.13.ffn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 51: blk.13.attn_k.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 52: blk.13.attn_output.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 53: blk.13.attn_q.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 54: blk.13.attn_v.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 55: blk.14.attn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 56: blk.14.ffn_down.weight q4_0 [ 11008, 4096, 1, 1 ]
llama_model_loader: - tensor 57: blk.14.ffn_gate.weight q4_0 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 58: blk.14.ffn_up.weight q4_0 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 59: blk.14.ffn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 60: blk.14.attn_k.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 61: blk.14.attn_output.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 62: blk.14.attn_q.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 63: blk.14.attn_v.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 64: blk.15.attn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 65: blk.15.ffn_down.weight q4_0 [ 11008, 4096, 1, 1 ]
llama_model_loader: - tensor 66: blk.15.ffn_gate.weight q4_0 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 67: blk.15.ffn_up.weight q4_0 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 68: blk.15.ffn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 69: blk.15.attn_k.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 70: blk.15.attn_output.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 71: blk.15.attn_q.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 72: blk.15.attn_v.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 73: blk.16.attn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 74: blk.16.ffn_down.weight q4_0 [ 11008, 4096, 1, 1 ]
llama_model_loader: - tensor 75: blk.16.ffn_gate.weight q4_0 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 76: blk.16.ffn_up.weight q4_0 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 77: blk.16.ffn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 78: blk.16.attn_k.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 79: blk.16.attn_output.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 80: blk.16.attn_q.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 81: blk.16.attn_v.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 82: blk.17.attn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 83: blk.17.ffn_down.weight q4_0 [ 11008, 4096, 1, 1 ]
llama_model_loader: - tensor 84: blk.17.ffn_gate.weight q4_0 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 85: blk.17.ffn_up.weight q4_0 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 86: blk.17.ffn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 87: blk.17.attn_k.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 88: blk.17.attn_output.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 89: blk.17.attn_q.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 90: blk.17.attn_v.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 91: blk.18.attn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 92: blk.18.ffn_down.weight q4_0 [ 11008, 4096, 1, 1 ]
llama_model_loader: - tensor 93: blk.18.ffn_gate.weight q4_0 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 94: blk.18.ffn_up.weight q4_0 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 95: blk.18.ffn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 96: blk.18.attn_k.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 97: blk.18.attn_output.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 98: blk.18.attn_q.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 99: blk.18.attn_v.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 100: blk.19.attn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 101: blk.19.ffn_down.weight q4_0 [ 11008, 4096, 1, 1 ]
llama_model_loader: - tensor 102: blk.19.ffn_gate.weight q4_0 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 103: blk.19.ffn_up.weight q4_0 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 104: blk.19.ffn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 105: blk.19.attn_k.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 106: blk.19.attn_output.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 107: blk.19.attn_q.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 108: blk.19.attn_v.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 109: blk.2.attn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 110: blk.2.ffn_down.weight q4_0 [ 11008, 4096, 1, 1 ]
llama_model_loader: - tensor 111: blk.2.ffn_gate.weight q4_0 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 112: blk.2.ffn_up.weight q4_0 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 113: blk.2.ffn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 114: blk.2.attn_k.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 115: blk.2.attn_output.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 116: blk.2.attn_q.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 117: blk.2.attn_v.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 118: blk.20.attn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 119: blk.20.ffn_down.weight q4_0 [ 11008, 4096, 1, 1 ]
llama_model_loader: - tensor 120: blk.20.ffn_gate.weight q4_0 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 121: blk.20.ffn_up.weight q4_0 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 122: blk.20.ffn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 123: blk.20.attn_k.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 124: blk.20.attn_output.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 125: blk.20.attn_q.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 126: blk.20.attn_v.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 127: blk.21.attn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 128: blk.21.ffn_down.weight q4_0 [ 11008, 4096, 1, 1 ]
llama_model_loader: - tensor 129: blk.21.ffn_gate.weight q4_0 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 130: blk.21.ffn_up.weight q4_0 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 131: blk.21.ffn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 132: blk.21.attn_k.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 133: blk.21.attn_output.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 134: blk.21.attn_q.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 135: blk.21.attn_v.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 136: blk.22.attn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 137: blk.22.ffn_down.weight q4_0 [ 11008, 4096, 1, 1 ]
llama_model_loader: - tensor 138: blk.22.ffn_gate.weight q4_0 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 139: blk.22.ffn_up.weight q4_0 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 140: blk.22.ffn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 141: blk.22.attn_k.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 142: blk.22.attn_output.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 143: blk.22.attn_q.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 144: blk.22.attn_v.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 145: blk.23.attn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 146: blk.23.ffn_down.weight q4_0 [ 11008, 4096, 1, 1 ]
llama_model_loader: - tensor 147: blk.23.ffn_gate.weight q4_0 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 148: blk.23.ffn_up.weight q4_0 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 149: blk.23.ffn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 150: blk.23.attn_k.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 151: blk.23.attn_output.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 152: blk.23.attn_q.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 153: blk.23.attn_v.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 154: blk.3.attn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 155: blk.3.ffn_down.weight q4_0 [ 11008, 4096, 1, 1 ]
llama_model_loader: - tensor 156: blk.3.ffn_gate.weight q4_0 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 157: blk.3.ffn_up.weight q4_0 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 158: blk.3.ffn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 159: blk.3.attn_k.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 160: blk.3.attn_output.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 161: blk.3.attn_q.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 162: blk.3.attn_v.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 163: blk.4.attn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 164: blk.4.ffn_down.weight q4_0 [ 11008, 4096, 1, 1 ]
llama_model_loader: - tensor 165: blk.4.ffn_gate.weight q4_0 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 166: blk.4.ffn_up.weight q4_0 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 167: blk.4.ffn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 168: blk.4.attn_k.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 169: blk.4.attn_output.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 170: blk.4.attn_q.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 171: blk.4.attn_v.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 172: blk.5.attn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 173: blk.5.ffn_down.weight q4_0 [ 11008, 4096, 1, 1 ]
llama_model_loader: - tensor 174: blk.5.ffn_gate.weight q4_0 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 175: blk.5.ffn_up.weight q4_0 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 176: blk.5.ffn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 177: blk.5.attn_k.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 178: blk.5.attn_output.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 179: blk.5.attn_q.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 180: blk.5.attn_v.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 181: blk.6.attn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 182: blk.6.ffn_down.weight q4_0 [ 11008, 4096, 1, 1 ]
llama_model_loader: - tensor 183: blk.6.ffn_gate.weight q4_0 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 184: blk.6.ffn_up.weight q4_0 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 185: blk.6.ffn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 186: blk.6.attn_k.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 187: blk.6.attn_output.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 188: blk.6.attn_q.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 189: blk.6.attn_v.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 190: blk.7.attn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 191: blk.7.ffn_down.weight q4_0 [ 11008, 4096, 1, 1 ]
llama_model_loader: - tensor 192: blk.7.ffn_gate.weight q4_0 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 193: blk.7.ffn_up.weight q4_0 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 194: blk.7.ffn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 195: blk.7.attn_k.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 196: blk.7.attn_output.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 197: blk.7.attn_q.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 198: blk.7.attn_v.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 199: blk.8.attn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 200: blk.8.ffn_down.weight q4_0 [ 11008, 4096, 1, 1 ]
llama_model_loader: - tensor 201: blk.8.ffn_gate.weight q4_0 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 202: blk.8.ffn_up.weight q4_0 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 203: blk.8.ffn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 204: blk.8.attn_k.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 205: blk.8.attn_output.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 206: blk.8.attn_q.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 207: blk.8.attn_v.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 208: blk.9.attn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 209: blk.9.ffn_down.weight q4_0 [ 11008, 4096, 1, 1 ]
llama_model_loader: - tensor 210: blk.9.ffn_gate.weight q4_0 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 211: blk.9.ffn_up.weight q4_0 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 212: blk.9.ffn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 213: blk.9.attn_k.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 214: blk.9.attn_output.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 215: blk.9.attn_q.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 216: blk.9.attn_v.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 217: output.weight q6_K [ 4096, 32000, 1, 1 ]
llama_model_loader: - tensor 218: blk.24.attn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 219: blk.24.ffn_down.weight q4_0 [ 11008, 4096, 1, 1 ]
llama_model_loader: - tensor 220: blk.24.ffn_gate.weight q4_0 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 221: blk.24.ffn_up.weight q4_0 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 222: blk.24.ffn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 223: blk.24.attn_k.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 224: blk.24.attn_output.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 225: blk.24.attn_q.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 226: blk.24.attn_v.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 227: blk.25.attn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 228: blk.25.ffn_down.weight q4_0 [ 11008, 4096, 1, 1 ]
llama_model_loader: - tensor 229: blk.25.ffn_gate.weight q4_0 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 230: blk.25.ffn_up.weight q4_0 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 231: blk.25.ffn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 232: blk.25.attn_k.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 233: blk.25.attn_output.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 234: blk.25.attn_q.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 235: blk.25.attn_v.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 236: blk.26.attn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 237: blk.26.ffn_down.weight q4_0 [ 11008, 4096, 1, 1 ]
llama_model_loader: - tensor 238: blk.26.ffn_gate.weight q4_0 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 239: blk.26.ffn_up.weight q4_0 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 240: blk.26.ffn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 241: blk.26.attn_k.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 242: blk.26.attn_output.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 243: blk.26.attn_q.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 244: blk.26.attn_v.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 245: blk.27.attn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 246: blk.27.ffn_down.weight q4_0 [ 11008, 4096, 1, 1 ]
llama_model_loader: - tensor 247: blk.27.ffn_gate.weight q4_0 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 248: blk.27.ffn_up.weight q4_0 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 249: blk.27.ffn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 250: blk.27.attn_k.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 251: blk.27.attn_output.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 252: blk.27.attn_q.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 253: blk.27.attn_v.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 254: blk.28.attn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 255: blk.28.ffn_down.weight q4_0 [ 11008, 4096, 1, 1 ]
llama_model_loader: - tensor 256: blk.28.ffn_gate.weight q4_0 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 257: blk.28.ffn_up.weight q4_0 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 258: blk.28.ffn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 259: blk.28.attn_k.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 260: blk.28.attn_output.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 261: blk.28.attn_q.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 262: blk.28.attn_v.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 263: blk.29.attn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 264: blk.29.ffn_down.weight q4_0 [ 11008, 4096, 1, 1 ]
llama_model_loader: - tensor 265: blk.29.ffn_gate.weight q4_0 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 266: blk.29.ffn_up.weight q4_0 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 267: blk.29.ffn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 268: blk.29.attn_k.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 269: blk.29.attn_output.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 270: blk.29.attn_q.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 271: blk.29.attn_v.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 272: blk.30.attn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 273: blk.30.ffn_down.weight q4_0 [ 11008, 4096, 1, 1 ]
llama_model_loader: - tensor 274: blk.30.ffn_gate.weight q4_0 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 275: blk.30.ffn_up.weight q4_0 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 276: blk.30.ffn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 277: blk.30.attn_k.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 278: blk.30.attn_output.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 279: blk.30.attn_q.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 280: blk.30.attn_v.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 281: blk.31.attn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 282: blk.31.ffn_down.weight q4_0 [ 11008, 4096, 1, 1 ]
llama_model_loader: - tensor 283: blk.31.ffn_gate.weight q4_0 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 284: blk.31.ffn_up.weight q4_0 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 285: blk.31.ffn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 286: blk.31.attn_k.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 287: blk.31.attn_output.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 288: blk.31.attn_q.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 289: blk.31.attn_v.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 290: output_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - kv 0: general.architecture str
llama_model_loader: - kv 1: general.name str
llama_model_loader: - kv 2: llama.context_length u32
llama_model_loader: - kv 3: llama.embedding_length u32
llama_model_loader: - kv 4: llama.block_count u32
llama_model_loader: - kv 5: llama.feed_forward_length u32
llama_model_loader: - kv 6: llama.rope.dimension_count u32
llama_model_loader: - kv 7: llama.attention.head_count u32
llama_model_loader: - kv 8: llama.attention.head_count_kv u32
llama_model_loader: - kv 9: llama.attention.layer_norm_rms_epsilon f32
llama_model_loader: - kv 10: general.file_type u32
llama_model_loader: - kv 11: tokenizer.ggml.model str
llama_model_loader: - kv 12: tokenizer.ggml.tokens arr
llama_model_loader: - kv 13: tokenizer.ggml.scores arr
llama_model_loader: - kv 14: tokenizer.ggml.token_type arr
llama_model_loader: - kv 15: tokenizer.ggml.bos_token_id u32
llama_model_loader: - kv 16: tokenizer.ggml.eos_token_id u32
llama_model_loader: - kv 17: tokenizer.ggml.unknown_token_id u32
llama_model_loader: - kv 18: general.quantization_version u32
llama_model_loader: - type f32: 65 tensors
llama_model_loader: - type q4_0: 225 tensors
llama_model_loader: - type q6_K: 1 tensors
llm_load_print_meta: format = GGUF V2 (latest)
llm_load_print_meta: arch = llama
llm_load_print_meta: vocab type = SPM
llm_load_print_meta: n_vocab = 32000
llm_load_print_meta: n_merges = 0
llm_load_print_meta: n_ctx_train = 4096
llm_load_print_meta: n_ctx = 512
llm_load_print_meta: n_embd = 4096
llm_load_print_meta: n_head = 32
llm_load_print_meta: n_head_kv = 32
llm_load_print_meta: n_layer = 32
llm_load_print_meta: n_rot = 128
llm_load_print_meta: n_gqa = 1
llm_load_print_meta: f_norm_eps = 1.0e-05
llm_load_print_meta: f_norm_rms_eps = 1.0e-06
llm_load_print_meta: n_ff = 11008
llm_load_print_meta: freq_base = 10000.0
llm_load_print_meta: freq_scale = 1
llm_load_print_meta: model type = 7B
llm_load_print_meta: model ftype = mostly Q4_0
llm_load_print_meta: model size = 6.74 B
llm_load_print_meta: general.name = LLaMA v2
llm_load_print_meta: BOS token = 1 '<s>'
llm_load_print_meta: EOS token = 2 '</s>'
llm_load_print_meta: UNK token = 0 '<unk>'
llm_load_print_meta: LF token = 13 '<0x0A>'
llm_load_tensors: ggml ctx size = 0.09 MB
llm_load_tensors: mem required = 3647.96 MB (+ 256.00 MB per state)
..................................................................................................
llama_new_context_with_model: kv self size = 256.00 MB
ggml_metal_init: allocating
ggml_metal_init: found device: Apple M1 Pro
ggml_metal_init: picking default device: Apple M1 Pro
ggml_metal_init: loading '/Users/agunapal/Documents/experiments/llama.cpp/ggml-metal.metal'
ggml_metal_init: loaded kernel_add 0x156808720 | th_max = 1024 | th_width = 32
ggml_metal_init: loaded kernel_add_row 0x155606aa0 | th_max = 1024 | th_width = 32
ggml_metal_init: loaded kernel_mul 0x1556071b0 | th_max = 1024 | th_width = 32
ggml_metal_init: loaded kernel_mul_row 0x155607820 | th_max = 1024 | th_width = 32
ggml_metal_init: loaded kernel_scale 0x156808d40 | th_max = 1024 | th_width = 32
ggml_metal_init: loaded kernel_silu 0x1568093a0 | th_max = 1024 | th_width = 32
ggml_metal_init: loaded kernel_relu 0x135604550 | th_max = 1024 | th_width = 32
ggml_metal_init: loaded kernel_gelu 0x135604cc0 | th_max = 1024 | th_width = 32
ggml_metal_init: loaded kernel_soft_max 0x155607c40 | th_max = 1024 | th_width = 32
ggml_metal_init: loaded kernel_soft_max_4 0x156809aa0 | th_max = 1024 | th_width = 32
ggml_metal_init: loaded kernel_diag_mask_inf 0x1556082e0 | th_max = 1024 | th_width = 32
ggml_metal_init: loaded kernel_diag_mask_inf_8 0x15680a2c0 | th_max = 1024 | th_width = 32
ggml_metal_init: loaded kernel_get_rows_f32 0x155608bb0 | th_max = 896 | th_width = 32
ggml_metal_init: loaded kernel_get_rows_f16 0x15680ab40 | th_max = 1024 | th_width = 32
ggml_metal_init: loaded kernel_get_rows_q4_0 0x1556092a0 | th_max = 1024 | th_width = 32
ggml_metal_init: loaded kernel_get_rows_q4_1 0x135605700 | th_max = 1024 | th_width = 32
ggml_metal_init: loaded kernel_get_rows_q8_0 0x15680b110 | th_max = 1024 | th_width = 32
ggml_metal_init: loaded kernel_get_rows_q2_K 0x155705460 | th_max = 1024 | th_width = 32
ggml_metal_init: loaded kernel_get_rows_q3_K 0x155609990 | th_max = 1024 | th_width = 32
ggml_metal_init: loaded kernel_get_rows_q4_K 0x15560a310 | th_max = 1024 | th_width = 32
ggml_metal_init: loaded kernel_get_rows_q5_K 0x15560aa00 | th_max = 1024 | th_width = 32
ggml_metal_init: loaded kernel_get_rows_q6_K 0x15560b0f0 | th_max = 1024 | th_width = 32
ggml_metal_init: loaded kernel_rms_norm 0x15680b810 | th_max = 1024 | th_width = 32
ggml_metal_init: loaded kernel_norm 0x15560bb50 | th_max = 1024 | th_width = 32
ggml_metal_init: loaded kernel_mul_mat_f32_f32 0x15560c730 | th_max = 1024 | th_width = 32
ggml_metal_init: loaded kernel_mul_mat_f16_f32 0x15680c230 | th_max = 1024 | th_width = 32
ggml_metal_init: loaded kernel_mul_mat_f16_f32_1row 0x15560d030 | th_max = 1024 | th_width = 32
ggml_metal_init: loaded kernel_mul_mat_f16_f32_l4 0x15680cd30 | th_max = 1024 | th_width = 32
ggml_metal_init: loaded kernel_mul_mat_q4_0_f32 0x15680d3b0 | th_max = 896 | th_width = 32
ggml_metal_init: loaded kernel_mul_mat_q4_1_f32 0x15680de30 | th_max = 896 | th_width = 32
ggml_metal_init: loaded kernel_mul_mat_q8_0_f32 0x125b041a0 | th_max = 1024 | th_width = 32
ggml_metal_init: loaded kernel_mul_mat_q2_K_f32 0x15680e530 | th_max = 640 | th_width = 32
ggml_metal_init: loaded kernel_mul_mat_q3_K_f32 0x15560d450 | th_max = 576 | th_width = 32
ggml_metal_init: loaded kernel_mul_mat_q4_K_f32 0x15680eaf0 | th_max = 576 | th_width = 32
ggml_metal_init: loaded kernel_mul_mat_q5_K_f32 0x15680f430 | th_max = 640 | th_width = 32
ggml_metal_init: loaded kernel_mul_mat_q6_K_f32 0x135606220 | th_max = 1024 | th_width = 32
ggml_metal_init: loaded kernel_mul_mm_f32_f32 0x15560dca0 | th_max = 768 | th_width = 32
ggml_metal_init: loaded kernel_mul_mm_f16_f32 0x15560e610 | th_max = 768 | th_width = 32
ggml_metal_init: loaded kernel_mul_mm_q4_0_f32 0x15560ee70 | th_max = 768 | th_width = 32
ggml_metal_init: loaded kernel_mul_mm_q8_0_f32 0x15560f6d0 | th_max = 768 | th_width = 32
ggml_metal_init: loaded kernel_mul_mm_q4_1_f32 0x135605fa0 | th_max = 768 | th_width = 32
ggml_metal_init: loaded kernel_mul_mm_q2_K_f32 0x155705e80 | th_max = 768 | th_width = 32
ggml_metal_init: loaded kernel_mul_mm_q3_K_f32 0x15560fe00 | th_max = 768 | th_width = 32
ggml_metal_init: loaded kernel_mul_mm_q4_K_f32 0x155610770 | th_max = 768 | th_width = 32
ggml_metal_init: loaded kernel_mul_mm_q5_K_f32 0x1557066d0 | th_max = 768 | th_width = 32
ggml_metal_init: loaded kernel_mul_mm_q6_K_f32 0x155610fd0 | th_max = 768 | th_width = 32
ggml_metal_init: loaded kernel_rope 0x135606f20 | th_max = 1024 | th_width = 32
ggml_metal_init: loaded kernel_alibi_f32 0x15680f0b0 | th_max = 1024 | th_width = 32
ggml_metal_init: loaded kernel_cpy_f32_f16 0x15560b510 | th_max = 1024 | th_width = 32
ggml_metal_init: loaded kernel_cpy_f32_f32 0x1568109c0 | th_max = 1024 | th_width = 32
ggml_metal_init: loaded kernel_cpy_f16_f16 0x1568113b0 | th_max = 1024 | th_width = 32
ggml_metal_init: hasUnifiedMemory = true
ggml_metal_init: recommendedMaxWorkingSetSize = 21845.34 MB
ggml_metal_init: maxTransferRate = built-in GPU
llama_new_context_with_model: compute buffer total size = 73.47 MB
llama_new_context_with_model: max tensor size = 102.54 MB
ggml_metal_add_buffer: allocated 'data ' buffer, size = 3648.58 MB, ( 3649.08 / 21845.34)
ggml_metal_add_buffer: allocated 'eval ' buffer, size = 1.48 MB, ( 3650.56 / 21845.34)
ggml_metal_add_buffer: allocated 'kv ' buffer, size = 258.00 MB, ( 3908.56 / 21845.34)
ggml_metal_add_buffer: allocated 'alloc ' buffer, size = 72.02 MB, ( 3980.58 / 21845.34)
system_info: n_threads = 8 / 10 | AVX = 0 | AVX2 = 0 | AVX512 = 0 | AVX512_VBMI = 0 | AVX512_VNNI = 0 | FMA = 0 | NEON = 1 | ARM_FMA = 1 | F16C = 0 | FP16_VA = 1 | WASM_SIMD = 0 | BLAS = 1 | SSE3 = 0 | SSSE3 = 0 | VSX = 0 |
sampling: repeat_last_n = 64, repeat_penalty = 1.100000, presence_penalty = 0.000000, frequency_penalty = 0.000000, top_k = 40, tfs_z = 1.000000, top_p = 0.950000, typical_p = 1.000000, temp = 0.800000, mirostat = 0, mirostat_lr = 0.100000, mirostat_ent = 5.000000
generate: n_ctx = 512, n_batch = 512, n_predict = -1, n_keep = 0
everybody's a winner,
nobody's a loser."
The lyrics are simple but catchy and convey the message of inclusivity and equality. The song has become an anthem for social justice movements and is often performed at rallies and protests. [end of text]
llama_print_timings: load time = 8431.53 ms
llama_print_timings: sample time = 41.06 ms / 57 runs ( 0.72 ms per token, 1388.35 tokens per second)
llama_print_timings: prompt eval time = 0.00 ms / 1 tokens ( 0.00 ms per token, inf tokens per second)
llama_print_timings: eval time = 1650.97 ms / 57 runs ( 28.96 ms per token, 34.53 tokens per second)
llama_print_timings: total time = 1706.70 ms
ggml_metal_free: deallocating
Log end
@abetlen I was able to avoid the errors by building like this
git clone https://github.com/abetlen/llama-cpp-python.git
cd llama-cpp-python
git submodule update --init --recursive
CMAKE_ARGS="-DLLAMA_METAL=on" pip install -e .
But I am getting an error in the init function
File "/Users/agunapal/Documents/experiments/llama-cpp-python/llama_cpp/llama.py", line 377, in __init__
assert self.ctx is not None
AssertionError
Full log
llama_model_loader: loaded meta data with 19 key-value pairs and 291 tensors from /Users/agunapal/Documents/experiments/llama/ggml-model-q4_0.gguf (version GGUF V2 (latest))
llama_model_loader: - tensor 0: token_embd.weight q4_0 [ 4096, 32000, 1, 1 ]
llama_model_loader: - tensor 1: blk.0.attn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 2: blk.0.ffn_down.weight q4_0 [ 11008, 4096, 1, 1 ]
llama_model_loader: - tensor 3: blk.0.ffn_gate.weight q4_0 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 4: blk.0.ffn_up.weight q4_0 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 5: blk.0.ffn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 6: blk.0.attn_k.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 7: blk.0.attn_output.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 8: blk.0.attn_q.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 9: blk.0.attn_v.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 10: blk.1.attn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 11: blk.1.ffn_down.weight q4_0 [ 11008, 4096, 1, 1 ]
llama_model_loader: - tensor 12: blk.1.ffn_gate.weight q4_0 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 13: blk.1.ffn_up.weight q4_0 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 14: blk.1.ffn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 15: blk.1.attn_k.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 16: blk.1.attn_output.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 17: blk.1.attn_q.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 18: blk.1.attn_v.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 19: blk.10.attn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 20: blk.10.ffn_down.weight q4_0 [ 11008, 4096, 1, 1 ]
llama_model_loader: - tensor 21: blk.10.ffn_gate.weight q4_0 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 22: blk.10.ffn_up.weight q4_0 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 23: blk.10.ffn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 24: blk.10.attn_k.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 25: blk.10.attn_output.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 26: blk.10.attn_q.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 27: blk.10.attn_v.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 28: blk.11.attn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 29: blk.11.ffn_down.weight q4_0 [ 11008, 4096, 1, 1 ]
llama_model_loader: - tensor 30: blk.11.ffn_gate.weight q4_0 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 31: blk.11.ffn_up.weight q4_0 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 32: blk.11.ffn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 33: blk.11.attn_k.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 34: blk.11.attn_output.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 35: blk.11.attn_q.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 36: blk.11.attn_v.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 37: blk.12.attn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 38: blk.12.ffn_down.weight q4_0 [ 11008, 4096, 1, 1 ]
llama_model_loader: - tensor 39: blk.12.ffn_gate.weight q4_0 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 40: blk.12.ffn_up.weight q4_0 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 41: blk.12.ffn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 42: blk.12.attn_k.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 43: blk.12.attn_output.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 44: blk.12.attn_q.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 45: blk.12.attn_v.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 46: blk.13.attn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 47: blk.13.ffn_down.weight q4_0 [ 11008, 4096, 1, 1 ]
llama_model_loader: - tensor 48: blk.13.ffn_gate.weight q4_0 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 49: blk.13.ffn_up.weight q4_0 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 50: blk.13.ffn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 51: blk.13.attn_k.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 52: blk.13.attn_output.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 53: blk.13.attn_q.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 54: blk.13.attn_v.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 55: blk.14.attn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 56: blk.14.ffn_down.weight q4_0 [ 11008, 4096, 1, 1 ]
llama_model_loader: - tensor 57: blk.14.ffn_gate.weight q4_0 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 58: blk.14.ffn_up.weight q4_0 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 59: blk.14.ffn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 60: blk.14.attn_k.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 61: blk.14.attn_output.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 62: blk.14.attn_q.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 63: blk.14.attn_v.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 64: blk.15.attn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 65: blk.15.ffn_down.weight q4_0 [ 11008, 4096, 1, 1 ]
llama_model_loader: - tensor 66: blk.15.ffn_gate.weight q4_0 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 67: blk.15.ffn_up.weight q4_0 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 68: blk.15.ffn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 69: blk.15.attn_k.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 70: blk.15.attn_output.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 71: blk.15.attn_q.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 72: blk.15.attn_v.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 73: blk.16.attn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 74: blk.16.ffn_down.weight q4_0 [ 11008, 4096, 1, 1 ]
llama_model_loader: - tensor 75: blk.16.ffn_gate.weight q4_0 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 76: blk.16.ffn_up.weight q4_0 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 77: blk.16.ffn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 78: blk.16.attn_k.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 79: blk.16.attn_output.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 80: blk.16.attn_q.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 81: blk.16.attn_v.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 82: blk.17.attn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 83: blk.17.ffn_down.weight q4_0 [ 11008, 4096, 1, 1 ]
llama_model_loader: - tensor 84: blk.17.ffn_gate.weight q4_0 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 85: blk.17.ffn_up.weight q4_0 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 86: blk.17.ffn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 87: blk.17.attn_k.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 88: blk.17.attn_output.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 89: blk.17.attn_q.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 90: blk.17.attn_v.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 91: blk.18.attn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 92: blk.18.ffn_down.weight q4_0 [ 11008, 4096, 1, 1 ]
llama_model_loader: - tensor 93: blk.18.ffn_gate.weight q4_0 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 94: blk.18.ffn_up.weight q4_0 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 95: blk.18.ffn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 96: blk.18.attn_k.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 97: blk.18.attn_output.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 98: blk.18.attn_q.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 99: blk.18.attn_v.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 100: blk.19.attn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 101: blk.19.ffn_down.weight q4_0 [ 11008, 4096, 1, 1 ]
llama_model_loader: - tensor 102: blk.19.ffn_gate.weight q4_0 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 103: blk.19.ffn_up.weight q4_0 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 104: blk.19.ffn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 105: blk.19.attn_k.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 106: blk.19.attn_output.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 107: blk.19.attn_q.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 108: blk.19.attn_v.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 109: blk.2.attn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 110: blk.2.ffn_down.weight q4_0 [ 11008, 4096, 1, 1 ]
llama_model_loader: - tensor 111: blk.2.ffn_gate.weight q4_0 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 112: blk.2.ffn_up.weight q4_0 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 113: blk.2.ffn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 114: blk.2.attn_k.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 115: blk.2.attn_output.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 116: blk.2.attn_q.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 117: blk.2.attn_v.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 118: blk.20.attn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 119: blk.20.ffn_down.weight q4_0 [ 11008, 4096, 1, 1 ]
llama_model_loader: - tensor 120: blk.20.ffn_gate.weight q4_0 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 121: blk.20.ffn_up.weight q4_0 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 122: blk.20.ffn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 123: blk.20.attn_k.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 124: blk.20.attn_output.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 125: blk.20.attn_q.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 126: blk.20.attn_v.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 127: blk.21.attn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 128: blk.21.ffn_down.weight q4_0 [ 11008, 4096, 1, 1 ]
llama_model_loader: - tensor 129: blk.21.ffn_gate.weight q4_0 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 130: blk.21.ffn_up.weight q4_0 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 131: blk.21.ffn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 132: blk.21.attn_k.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 133: blk.21.attn_output.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 134: blk.21.attn_q.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 135: blk.21.attn_v.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 136: blk.22.attn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 137: blk.22.ffn_down.weight q4_0 [ 11008, 4096, 1, 1 ]
llama_model_loader: - tensor 138: blk.22.ffn_gate.weight q4_0 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 139: blk.22.ffn_up.weight q4_0 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 140: blk.22.ffn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 141: blk.22.attn_k.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 142: blk.22.attn_output.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 143: blk.22.attn_q.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 144: blk.22.attn_v.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 145: blk.23.attn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 146: blk.23.ffn_down.weight q4_0 [ 11008, 4096, 1, 1 ]
llama_model_loader: - tensor 147: blk.23.ffn_gate.weight q4_0 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 148: blk.23.ffn_up.weight q4_0 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 149: blk.23.ffn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 150: blk.23.attn_k.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 151: blk.23.attn_output.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 152: blk.23.attn_q.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 153: blk.23.attn_v.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 154: blk.3.attn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 155: blk.3.ffn_down.weight q4_0 [ 11008, 4096, 1, 1 ]
llama_model_loader: - tensor 156: blk.3.ffn_gate.weight q4_0 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 157: blk.3.ffn_up.weight q4_0 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 158: blk.3.ffn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 159: blk.3.attn_k.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 160: blk.3.attn_output.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 161: blk.3.attn_q.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 162: blk.3.attn_v.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 163: blk.4.attn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 164: blk.4.ffn_down.weight q4_0 [ 11008, 4096, 1, 1 ]
llama_model_loader: - tensor 165: blk.4.ffn_gate.weight q4_0 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 166: blk.4.ffn_up.weight q4_0 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 167: blk.4.ffn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 168: blk.4.attn_k.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 169: blk.4.attn_output.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 170: blk.4.attn_q.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 171: blk.4.attn_v.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 172: blk.5.attn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 173: blk.5.ffn_down.weight q4_0 [ 11008, 4096, 1, 1 ]
llama_model_loader: - tensor 174: blk.5.ffn_gate.weight q4_0 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 175: blk.5.ffn_up.weight q4_0 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 176: blk.5.ffn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 177: blk.5.attn_k.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 178: blk.5.attn_output.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 179: blk.5.attn_q.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 180: blk.5.attn_v.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 181: blk.6.attn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 182: blk.6.ffn_down.weight q4_0 [ 11008, 4096, 1, 1 ]
llama_model_loader: - tensor 183: blk.6.ffn_gate.weight q4_0 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 184: blk.6.ffn_up.weight q4_0 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 185: blk.6.ffn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 186: blk.6.attn_k.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 187: blk.6.attn_output.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 188: blk.6.attn_q.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 189: blk.6.attn_v.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 190: blk.7.attn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 191: blk.7.ffn_down.weight q4_0 [ 11008, 4096, 1, 1 ]
llama_model_loader: - tensor 192: blk.7.ffn_gate.weight q4_0 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 193: blk.7.ffn_up.weight q4_0 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 194: blk.7.ffn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 195: blk.7.attn_k.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 196: blk.7.attn_output.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 197: blk.7.attn_q.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 198: blk.7.attn_v.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 199: blk.8.attn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 200: blk.8.ffn_down.weight q4_0 [ 11008, 4096, 1, 1 ]
llama_model_loader: - tensor 201: blk.8.ffn_gate.weight q4_0 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 202: blk.8.ffn_up.weight q4_0 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 203: blk.8.ffn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 204: blk.8.attn_k.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 205: blk.8.attn_output.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 206: blk.8.attn_q.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 207: blk.8.attn_v.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 208: blk.9.attn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 209: blk.9.ffn_down.weight q4_0 [ 11008, 4096, 1, 1 ]
llama_model_loader: - tensor 210: blk.9.ffn_gate.weight q4_0 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 211: blk.9.ffn_up.weight q4_0 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 212: blk.9.ffn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 213: blk.9.attn_k.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 214: blk.9.attn_output.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 215: blk.9.attn_q.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 216: blk.9.attn_v.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 217: output.weight q6_K [ 4096, 32000, 1, 1 ]
llama_model_loader: - tensor 218: blk.24.attn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 219: blk.24.ffn_down.weight q4_0 [ 11008, 4096, 1, 1 ]
llama_model_loader: - tensor 220: blk.24.ffn_gate.weight q4_0 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 221: blk.24.ffn_up.weight q4_0 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 222: blk.24.ffn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 223: blk.24.attn_k.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 224: blk.24.attn_output.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 225: blk.24.attn_q.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 226: blk.24.attn_v.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 227: blk.25.attn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 228: blk.25.ffn_down.weight q4_0 [ 11008, 4096, 1, 1 ]
llama_model_loader: - tensor 229: blk.25.ffn_gate.weight q4_0 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 230: blk.25.ffn_up.weight q4_0 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 231: blk.25.ffn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 232: blk.25.attn_k.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 233: blk.25.attn_output.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 234: blk.25.attn_q.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 235: blk.25.attn_v.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 236: blk.26.attn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 237: blk.26.ffn_down.weight q4_0 [ 11008, 4096, 1, 1 ]
llama_model_loader: - tensor 238: blk.26.ffn_gate.weight q4_0 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 239: blk.26.ffn_up.weight q4_0 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 240: blk.26.ffn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 241: blk.26.attn_k.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 242: blk.26.attn_output.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 243: blk.26.attn_q.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 244: blk.26.attn_v.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 245: blk.27.attn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 246: blk.27.ffn_down.weight q4_0 [ 11008, 4096, 1, 1 ]
llama_model_loader: - tensor 247: blk.27.ffn_gate.weight q4_0 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 248: blk.27.ffn_up.weight q4_0 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 249: blk.27.ffn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 250: blk.27.attn_k.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 251: blk.27.attn_output.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 252: blk.27.attn_q.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 253: blk.27.attn_v.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 254: blk.28.attn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 255: blk.28.ffn_down.weight q4_0 [ 11008, 4096, 1, 1 ]
llama_model_loader: - tensor 256: blk.28.ffn_gate.weight q4_0 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 257: blk.28.ffn_up.weight q4_0 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 258: blk.28.ffn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 259: blk.28.attn_k.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 260: blk.28.attn_output.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 261: blk.28.attn_q.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 262: blk.28.attn_v.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 263: blk.29.attn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 264: blk.29.ffn_down.weight q4_0 [ 11008, 4096, 1, 1 ]
llama_model_loader: - tensor 265: blk.29.ffn_gate.weight q4_0 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 266: blk.29.ffn_up.weight q4_0 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 267: blk.29.ffn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 268: blk.29.attn_k.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 269: blk.29.attn_output.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 270: blk.29.attn_q.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 271: blk.29.attn_v.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 272: blk.30.attn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 273: blk.30.ffn_down.weight q4_0 [ 11008, 4096, 1, 1 ]
llama_model_loader: - tensor 274: blk.30.ffn_gate.weight q4_0 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 275: blk.30.ffn_up.weight q4_0 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 276: blk.30.ffn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 277: blk.30.attn_k.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 278: blk.30.attn_output.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 279: blk.30.attn_q.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 280: blk.30.attn_v.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 281: blk.31.attn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 282: blk.31.ffn_down.weight q4_0 [ 11008, 4096, 1, 1 ]
llama_model_loader: - tensor 283: blk.31.ffn_gate.weight q4_0 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 284: blk.31.ffn_up.weight q4_0 [ 4096, 11008, 1, 1 ]
llama_model_loader: - tensor 285: blk.31.ffn_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - tensor 286: blk.31.attn_k.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 287: blk.31.attn_output.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 288: blk.31.attn_q.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 289: blk.31.attn_v.weight q4_0 [ 4096, 4096, 1, 1 ]
llama_model_loader: - tensor 290: output_norm.weight f32 [ 4096, 1, 1, 1 ]
llama_model_loader: - kv 0: general.architecture str
llama_model_loader: - kv 1: general.name str
llama_model_loader: - kv 2: llama.context_length u32
llama_model_loader: - kv 3: llama.embedding_length u32
llama_model_loader: - kv 4: llama.block_count u32
llama_model_loader: - kv 5: llama.feed_forward_length u32
llama_model_loader: - kv 6: llama.rope.dimension_count u32
llama_model_loader: - kv 7: llama.attention.head_count u32
llama_model_loader: - kv 8: llama.attention.head_count_kv u32
llama_model_loader: - kv 9: llama.attention.layer_norm_rms_epsilon f32
llama_model_loader: - kv 10: general.file_type u32
llama_model_loader: - kv 11: tokenizer.ggml.model str
llama_model_loader: - kv 12: tokenizer.ggml.tokens arr
llama_model_loader: - kv 13: tokenizer.ggml.scores arr
llama_model_loader: - kv 14: tokenizer.ggml.token_type arr
llama_model_loader: - kv 15: tokenizer.ggml.bos_token_id u32
llama_model_loader: - kv 16: tokenizer.ggml.eos_token_id u32
llama_model_loader: - kv 17: tokenizer.ggml.unknown_token_id u32
llama_model_loader: - kv 18: general.quantization_version u32
llama_model_loader: - type f32: 65 tensors
llama_model_loader: - type q4_0: 225 tensors
llama_model_loader: - type q6_K: 1 tensors
llm_load_print_meta: format = GGUF V2 (latest)
llm_load_print_meta: arch = llama
llm_load_print_meta: vocab type = SPM
llm_load_print_meta: n_vocab = 32000
llm_load_print_meta: n_merges = 0
llm_load_print_meta: n_ctx_train = 4096
llm_load_print_meta: n_embd = 4096
llm_load_print_meta: n_head = 32
llm_load_print_meta: n_head_kv = 32
llm_load_print_meta: n_layer = 32
llm_load_print_meta: n_rot = 128
llm_load_print_meta: n_gqa = 1
llm_load_print_meta: f_norm_eps = 0.0e+00
llm_load_print_meta: f_norm_rms_eps = 1.0e-06
llm_load_print_meta: n_ff = 11008
llm_load_print_meta: freq_base_train = 10000.0
llm_load_print_meta: freq_scale_train = 1
llm_load_print_meta: model type = 7B
llm_load_print_meta: model ftype = mostly Q4_0
llm_load_print_meta: model params = 6.74 B
llm_load_print_meta: model size = 3.56 GiB (4.54 BPW)
llm_load_print_meta: general.name = LLaMA v2
llm_load_print_meta: BOS token = 1 '<s>'
llm_load_print_meta: EOS token = 2 '</s>'
llm_load_print_meta: UNK token = 0 '<unk>'
llm_load_print_meta: LF token = 13 '<0x0A>'
llm_load_tensors: ggml ctx size = 0.09 MB
llm_load_tensors: mem required = 3647.96 MB
..................................................................................................
llama_new_context_with_model: n_ctx = 512
llama_new_context_with_model: freq_base = 10000.0
llama_new_context_with_model: freq_scale = 1
llama_new_context_with_model: kv self size = 256.00 MB
llama_new_context_with_model: ggml_metal_init() failed
Traceback (most recent call last):
File "/Users/agunapal/Documents/pytorch/fork/serve/examples/LLM/llama2/chat_app/test.py", line 3, in <module>
llm = Llama(model_path="/Users/agunapal/Documents/experiments/llama/ggml-model-q4_0.gguf", n_gpu_layers=-1, verbose=True)
File "/Users/agunapal/Documents/experiments/llama-cpp-python/llama_cpp/llama.py", line 377, in __init__
assert self.ctx is not None
AssertionError
hmmm.. that doesn't seem to make a difference
Traceback (most recent call last):
File "/Users/agunapal/Documents/pytorch/fork/serve/examples/LLM/llama2/chat_app/test.py", line 3, in <module>
llm = Llama(model_path="/Users/agunapal/Documents/experiments/llama/ggml-model-q4_0.gguf", n_gpu_layers=1)
File "/Users/agunapal/Documents/experiments/llama-cpp-python/llama_cpp/llama.py", line 377, in __init__
assert self.ctx is not None
AssertionError
@abetlen Here is the output of otool. Seems like the versions are different and llama-cpp is using older versions for some of these. I couldn't figure out in the code where these differences are coming from?
for llama.cpp
otool -L main
main:
/System/Library/Frameworks/Accelerate.framework/Versions/A/Accelerate (compatibility version 1.0.0, current version 4.0.0)
/System/Library/Frameworks/Foundation.framework/Versions/C/Foundation (compatibility version 300.0.0, current version 1971.0.0)
/System/Library/Frameworks/Metal.framework/Versions/A/Metal (compatibility version 1.0.0, current version 306.5.16)
/System/Library/Frameworks/MetalKit.framework/Versions/A/MetalKit (compatibility version 1.0.0, current version 157.0.0)
/usr/lib/libc++.1.dylib (compatibility version 1.0.0, current version 1500.65.0)
/usr/lib/libSystem.B.dylib (compatibility version 1.0.0, current version 1319.100.3)
/System/Library/Frameworks/CoreFoundation.framework/Versions/A/CoreFoundation (compatibility version 150.0.0, current version 1971.0.0)
/usr/lib/libobjc.A.dylib (compatibility version 1.0.0, current version 228.0.0)
for llama-cpp-python
otool -L libllama.dylib
libllama.dylib:
@rpath/libllama.dylib (compatibility version 0.0.0, current version 0.0.0)
/System/Library/Frameworks/Accelerate.framework/Versions/A/Accelerate (compatibility version 1.0.0, current version 4.0.0)
/System/Library/Frameworks/Foundation.framework/Versions/C/Foundation (compatibility version 300.0.0, current version 2048.1.255)
/System/Library/Frameworks/Metal.framework/Versions/A/Metal (compatibility version 1.0.0, current version 341.16.0)
/System/Library/Frameworks/MetalKit.framework/Versions/A/MetalKit (compatibility version 1.0.0, current version 159.0.0)
/usr/lib/libc++.1.dylib (compatibility version 1.0.0, current version 1600.151.0)
/usr/lib/libSystem.B.dylib (compatibility version 1.0.0, current version 1336.0.0)
/System/Library/Frameworks/CoreFoundation.framework/Versions/A/CoreFoundation (compatibility version 150.0.0, current version 2048.1.255)
/usr/lib/libobjc.A.dylib (compatibility version 1.0.0, current version 228.0.0)
https://github.com/pytorch/serve/tree/master/examples/LLM/llama2/chat_app
so "n_gpu_layers" is always recommended? I got an Apple M2 Max chip, with 12 cores and 64gb RAM. Also what number of "n_batch" would you suggest with this setting?
@xuyang06 The issue is caused by running an x86 version of Python. I also had this issue as by default on a Mac Python is installed as x86 with Rosetta. I installed the Arm64 version and everything ran correctly.
You can see if you are running x86 by calling the following command: import platform print(platform.platform())
which will probably report: macOS-10.16-x86_64-i386-64bit it needs to be macOS-14.2.1-arm64-arm-64bit
Hi all - same issue here, I am on most recent version of MacOS (on a Macbook Pro M2 MAX), and I copied/pasted the install instructions multiple times, so there's no change I messed up - I have tried uninstalling & reinstalling multiple times, I have triple-checked my conda env, etc.
Trying to use the --n_gpu_layers -1 flag (-1 is for all layers but tried with other numbers too) does NOT work, results in the same as or slower than CPU-only inference.
I was doing some googling though and I came across #375 from last summer. I tried switching my conda env to base, and it immediately worked - setting --n_gpu_layers -1 in the llama env results in cpu-like-or-slower inference, but switching back to base results in incredibly fast performance.
Seems like this is a known issue that is re-surfacing?
@xuyang06 The issue is caused by running an x86 version of Python. I also had this issue as by default on a Mac Python is installed as x86 with Rosetta. I installed the Arm64 version and everything ran correctly.
You can see if you are running x86 by calling the following command: import platform print(platform.platform())
which will probably report: macOS-10.16-x86_64-i386-64bit it needs to be macOS-14.2.1-arm64-arm-64bit
For what it's worth, the install docs for Apple Silicon do make it clear that you have to install a Silicon-compatible-and-optimized version of Python, which I made sure to do -- https://llama-cpp-python.readthedocs.io/en/latest/install/macos/
I have an M2 chip and I've noticed something :
- When I use an earlier version
llama-cpp-python==0.1.83then my GPU is activated :) - However when I use the current version, then nope! Only CPU :(. I don't know exactly the reason but it would be nice to find out why.
same for me @hbacard . I first had llama-cpp-python 0.2.27 installed and now upgraded to 0.2.39 and with the newer version my responses take 15s longer than before
It is the same on my m1 Mac Studio, llama_cpp_python==0.2.43:
- When running python code, it takes 16s on the "load time" , 3.4 tokens/sec. The GPU usage is about 10%.
- When running in llama.cpp main command line, it takes only 2-3 seconds on the "load time", 7 tokens/sec, The GPU usage is about 99%.
the llama-cpp-python was installed by any of the two commands (get the same results):
CMAKE_ARGS="-DLLAMA_METAL=on" FORCE_CMAKE=1 pip install --upgrade --force-reinstall llama-cpp-python --no-cache-dir
CMAKE_ARGS="-DLLAMA_METAL=on" pip install llama-cpp-python # for this command, uninstall firstly
Python Code Output:
llama_print_timings: load time = 16110.36 ms
llama_print_timings: sample time = 68.56 ms / 886 runs ( 0.08 ms per token, 12923.93 tokens per second)
llama_print_timings: prompt eval time = 16110.05 ms / 250 tokens ( 64.44 ms per token, 15.52 tokens per second)
llama_print_timings: eval time = 257733.85 ms / 885 runs ( 291.22 ms per token, 3.43 tokens per second)
llama_print_timings: total time = 275696.64 ms / 1135 tokens
This test case checks that the rate limiter works as expected for calls within and outside the interval, as well as after the interval expires. ggml_metal_free: deallocating
For llama-cpp-python, the GPU usage is low, and most of the power is consumed by CPU:
llama.cpp executable output:
llama_print_timings: load time = 2212.00 ms
llama_print_timings: sample time = 88.95 ms / 948 runs ( 0.09 ms per token, 10658.03 tokens per second)
llama_print_timings: prompt eval time = 4114.82 ms / 256 tokens ( 16.07 ms per token, 62.21 tokens per second)
llama_print_timings: eval time = 136452.01 ms / 947 runs ( 144.09 ms per token, 6.94 tokens per second)
llama_print_timings: total time = 140811.12 ms
ggml_metal_free: deallocating
Log end
For llama.cpp main, the GPU usage is 99%~100%, and almost all the power consumption is on the GPU:
same for me @hbacard . I first had llama-cpp-python 0.2.27 installed and now upgraded to 0.2.39 and with the newer version my responses take 15s longer than before
I've confirmed that the llama-cpp-python 0.2.27 works, I installed this version, and it has almost the same loading time and inference speed as the c++ version of llama.cpp. Also the GPU usage increased to 100%. Thank you.
pip uninstall llama-cpp-python
CMAKE_ARGS="-DLLAMA_METAL=on" pip install llama-cpp-python==0.2.27
Now, the python code inference speed :
llama_print_timings: load time = 5264.41 ms
llama_print_timings: sample time = 95.59 ms / 982 runs ( 0.10 ms per token, 10273.04 tokens per second)
llama_print_timings: prompt eval time = 5264.07 ms / 250 tokens ( 21.06 ms per token, 47.49 tokens per second)
llama_print_timings: eval time = 141315.24 ms / 981 runs ( 144.05 ms per token, 6.94 tokens per second)
llama_print_timings: total time = 148496.25 ms
unittest.main() ggml_metal_free: deallocating
same for me @hbacard . I first had llama-cpp-python 0.2.27 installed and now upgraded to 0.2.39 and with the newer version my responses take 15s longer than before
I've confirmed that the llama-cpp-python 0.2.27 works, I installed this version, and it has almost the same loading time and inference speed as the c++ version of llama.cpp. Also the GPU usage increased to 100%. Thank you.
pip uninstall llama-cpp-python CMAKE_ARGS="-DLLAMA_METAL=on" pip install llama-cpp-python==0.2.27Now, the python code inference speed :
llama_print_timings: load time = 5264.41 ms llama_print_timings: sample time = 95.59 ms / 982 runs ( 0.10 ms per token, 10273.04 tokens per second) llama_print_timings: prompt eval time = 5264.07 ms / 250 tokens ( 21.06 ms per token, 47.49 tokens per second) llama_print_timings: eval time = 141315.24 ms / 981 runs ( 144.05 ms per token, 6.94 tokens per second) llama_print_timings: total time = 148496.25 ms unittest.main() ggml_metal_free: deallocating
Thanks to the experiments, version 0.2.27 is a perfect fit for the M2 Pro
Hi, apologies for the basic question, I'm still a beginner with llama-cpp-python.
Downloaded a 7b quantized small model directly from the website and put it in the working directory, loaded it, and ran it, probably completely in the CPU. I have an M1 mac with 8gb of memory. It's taking about 5 minutes to generate short responses with short context, is this normal? What can I do to optimize this? Should I be connecting to the GPU, do I have any other options? I need to keep it running locally, not on the cloud. I have another older laptop, intel chip 16gb, would it likely perform better there?
8gb memory it not enough to run 7b quantized model smoothly. Even on my 18GB mac m3, it is slow. You need more memory on m1/m2/m3. For intel chip, it may output about 5 tokens per seconds for a quantized 7b/13b models.
5 Tokens per second is pretty fast, that's a much better performance than what I was getting on the 8gb M1 (about 20 words so probably around 40 tokens in 5 minutes). Ideally, I want to use about 2 paragraphs of context for the answer, do you think this would also cause the 16gb machine to slow down significantly? I can't test it yet for non-technical reasons, but I hope to be able to in the coming week.
On Wed, Jul 10, 2024 at 10:59 PM david l euler @.***> wrote:
8gb memory it not enough to run 7b quantized model smoothly. Even on my 18GB mac m3, it is slow. You need more memory on m1/m2/m3. For intel chip, it may output about 5 tokens per seconds for a quantized 7b/13b models.
— Reply to this email directly, view it on GitHub https://urldefense.proofpoint.com/v2/url?u=https-3A__github.com_abetlen_llama-2Dcpp-2Dpython_issues_756-23issuecomment-2D2222098169&d=DwMCaQ&c=slrrB7dE8n7gBJbeO0g-IQ&r=AW1LAWv_WqVxDO6aYfatyA&m=hENhMwk3f_PDcWffQ7btzf2Mf7899ZipJOviYcVSxGyEx6nZqLSRh71kVt5In5lY&s=mNdft_uTG266kgO2zYbZZQwL_dOEeiCG1oNlO0LygSk&e=, or unsubscribe https://urldefense.proofpoint.com/v2/url?u=https-3A__github.com_notifications_unsubscribe-2Dauth_A64Q7SRIZXAMKHU5ODXZWH3ZLYNM7AVCNFSM6AAAAAA5IGQ3J6VHI2DSMVQWIX3LMV43OSLTON2WKQ3PNVWWK3TUHMZDEMRSGA4TQMJWHE&d=DwMCaQ&c=slrrB7dE8n7gBJbeO0g-IQ&r=AW1LAWv_WqVxDO6aYfatyA&m=hENhMwk3f_PDcWffQ7btzf2Mf7899ZipJOviYcVSxGyEx6nZqLSRh71kVt5In5lY&s=_04-IAs9WPyedOMqdyXa6Ph1E18gbBrgW-FG7jAr8-s&e= . You are receiving this because you commented.Message ID: @.***>
