PygmalionAI
[Bug]: Several errors when deploying GGUF models
Your current environment
The output of `python env.py`
Collecting environment information... PyTorch version: 2.4.0+cu121 Is debug build: False CUDA used to build PyTorch: 12.1 ROCM used to build PyTorch: N/A
OS: Pop!_OS 22.04 LTS (x86_64) GCC version: (Ubuntu 11.4.0-1ubuntu1~22.04) 11.4.0 Clang version: Could not collect CMake version: Could not collect Libc version: glibc-2.35
Python version: 3.10.12 (main, Mar 22 2024, 16:50:05) [GCC 11.4.0] (64-bit runtime) Python platform: Linux-6.9.3-76060903-generic-x86_64-with-glibc2.35 Is CUDA available: True CUDA runtime version: Could not collect CUDA_MODULE_LOADING set to: LAZY GPU models and configuration: GPU 0: NVIDIA GeForce RTX 3050 Ti Laptop GPU Nvidia driver version: 550.67 cuDNN version: Could not collect HIP runtime version: N/A MIOpen runtime version: N/A Is XNNPACK available: True
CPU: Architecture: x86_64 CPU op-mode(s): 32-bit, 64-bit Address sizes: 39 bits physical, 48 bits virtual Byte Order: Little Endian CPU(s): 12 On-line CPU(s) list: 0-11 Vendor ID: GenuineIntel Model name: 11th Gen Intel(R) Core(TM) i5-11400H @ 2.70GHz CPU family: 6 Model: 141 Thread(s) per core: 2 Core(s) per socket: 6 Socket(s): 1 Stepping: 1 CPU max MHz: 4500.0000 CPU min MHz: 800.0000 BogoMIPS: 5376.00 Flags: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe syscall nx pdpe1gb rdtscp lm constant_tsc art arch_perfmon pebs bts rep_good nopl xtopology nonstop_tsc cpuid aperfmperf tsc_known_freq pni pclmulqdq dtes64 monitor ds_cpl vmx est tm2 ssse3 sdbg fma cx16 xtpr pdcm pcid sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand lahf_lm abm 3dnowprefetch cpuid_fault epb cat_l2 cdp_l2 ssbd ibrs ibpb stibp ibrs_enhanced tpr_shadow flexpriority ept vpid ept_ad fsgsbase tsc_adjust bmi1 avx2 smep bmi2 erms invpcid rdt_a avx512f avx512dq rdseed adx smap avx512ifma clflushopt clwb intel_pt avx512cd sha_ni avx512bw avx512vl xsaveopt xsavec xgetbv1 xsaves split_lock_detect user_shstk dtherm ida arat pln pts hwp hwp_notify hwp_act_window hwp_epp hwp_pkg_req vnmi avx512vbmi umip pku ospke avx512_vbmi2 gfni vaes vpclmulqdq avx512_vnni avx512_bitalg avx512_vpopcntdq rdpid movdiri movdir64b fsrm avx512_vp2intersect md_clear ibt flush_l1d arch_capabilities Virtualisation: VT-x L1d cache: 288 KiB (6 instances) L1i cache: 192 KiB (6 instances) L2 cache: 7.5 MiB (6 instances) L3 cache: 12 MiB (1 instance) NUMA node(s): 1 NUMA node0 CPU(s): 0-11 Vulnerability Gather data sampling: Mitigation; Microcode Vulnerability Itlb multihit: Not affected Vulnerability L1tf: Not affected Vulnerability Mds: Not affected Vulnerability Meltdown: Not affected Vulnerability Mmio stale data: Not affected Vulnerability Reg file data sampling: Not affected Vulnerability Retbleed: Not affected Vulnerability Spec rstack overflow: Not affected Vulnerability Spec store bypass: Mitigation; Speculative Store Bypass disabled via prctl Vulnerability Spectre v1: Mitigation; usercopy/swapgs barriers and __user pointer sanitization Vulnerability Spectre v2: Mitigation; Enhanced / Automatic IBRS; IBPB conditional; RSB filling; PBRSB-eIBRS SW sequence; BHI SW loop, KVM SW loop Vulnerability Srbds: Not affected Vulnerability Tsx async abort: Not affected
Versions of relevant libraries: [pip3] numpy==1.26.4 [pip3] nvidia-nccl-cu12==2.20.5 [pip3] pyzmq==26.2.0 [pip3] torch==2.4.0 [pip3] torchvision==0.19.0 [pip3] transformers==4.45.2 [pip3] triton==3.0.0 [conda] No relevant packages ROCM Version: Could not collect Neuron SDK Version: N/A Aphrodite Version: 0.6.2.post1 Aphrodite Build Flags: CUDA Archs: Not Set; ROCm: Disabled; Neuron: Disabled GPU Topology: [4mGPU0 CPU Affinity NUMA Affinity GPU NUMA ID[0m GPU0 X 0-11 0 N/A
Legend:
X = Self SYS = Connection traversing PCIe as well as the SMP interconnect between NUMA nodes (e.g., QPI/UPI) NODE = Connection traversing PCIe as well as the interconnect between PCIe Host Bridges within a NUMA node PHB = Connection traversing PCIe as well as a PCIe Host Bridge (typically the CPU) PXB = Connection traversing multiple PCIe bridges (without traversing the PCIe Host Bridge) PIX = Connection traversing at most a single PCIe bridge NV# = Connection traversing a bonded set of # NVLinks
🐛 Describe the bug
When deploying GGUF models, I am getting errors (different depending on the models).
Deployment method:
python -m aphrodite.endpoints.openai.api_server --model <local-path-to-gguf-model>
Here are two that I've encountered:
Llama-3.2-1B-Instruct-Uncensored.Q6_K.gguf from mradermacher/Llama-3.2-1B-Instruct-Uncensored-GGUF
INFO: Loading model Llama-3.2-1B-Instruct-Uncensored.Q6_K.gguf...
Process SpawnProcess-1:
Traceback (most recent call last):
File "/usr/lib/python3.10/multiprocessing/process.py", line 314, in _bootstrap
self.run()
File "/usr/lib/python3.10/multiprocessing/process.py", line 108, in run
self._target(*self._args, **self._kwargs)
File "/home/carlosfm/kalavai/kalavai-client/templates/aphrodite/env/lib/python3.10/site-packages/aphrodite/endpoints/openai/rpc/server.py", line 209, in run_rpc_server
server = AsyncEngineRPCServer(async_engine_args, rpc_path)
File "/home/carlosfm/kalavai/kalavai-client/templates/aphrodite/env/lib/python3.10/site-packages/aphrodite/endpoints/openai/rpc/server.py", line 24, in __init__
self.engine = AsyncAphrodite.from_engine_args(async_engine_args)
File "/home/carlosfm/kalavai/kalavai-client/templates/aphrodite/env/lib/python3.10/site-packages/aphrodite/engine/async_aphrodite.py", line 601, in from_engine_args
engine = cls(
File "/home/carlosfm/kalavai/kalavai-client/templates/aphrodite/env/lib/python3.10/site-packages/aphrodite/engine/async_aphrodite.py", line 510, in __init__
self.engine = self._init_engine(*args, **kwargs)
File "/home/carlosfm/kalavai/kalavai-client/templates/aphrodite/env/lib/python3.10/site-packages/aphrodite/engine/async_aphrodite.py", line 694, in _init_engine
return engine_class(*args, **kwargs)
File "/home/carlosfm/kalavai/kalavai-client/templates/aphrodite/env/lib/python3.10/site-packages/aphrodite/engine/aphrodite_engine.py", line 261, in __init__
self.model_executor = executor_class(
File "/home/carlosfm/kalavai/kalavai-client/templates/aphrodite/env/lib/python3.10/site-packages/aphrodite/executor/executor_base.py", line 45, in __init__
self._init_executor()
File "/home/carlosfm/kalavai/kalavai-client/templates/aphrodite/env/lib/python3.10/site-packages/aphrodite/executor/gpu_executor.py", line 36, in _init_executor
self.driver_worker.load_model()
File "/home/carlosfm/kalavai/kalavai-client/templates/aphrodite/env/lib/python3.10/site-packages/aphrodite/task_handler/worker.py", line 153, in load_model
self.model_runner.load_model()
File "/home/carlosfm/kalavai/kalavai-client/templates/aphrodite/env/lib/python3.10/site-packages/aphrodite/task_handler/model_runner.py", line 888, in load_model
self.model = get_model(model_config=self.model_config,
File "/home/carlosfm/kalavai/kalavai-client/templates/aphrodite/env/lib/python3.10/site-packages/aphrodite/modeling/model_loader/__init__.py", line 20, in get_model
return loader.load_model(model_config=model_config,
File "/home/carlosfm/kalavai/kalavai-client/templates/aphrodite/env/lib/python3.10/site-packages/aphrodite/modeling/model_loader/loader.py", line 1033, in load_model
model = _initialize_model(model_config, self.load_config,
File "/home/carlosfm/kalavai/kalavai-client/templates/aphrodite/env/lib/python3.10/site-packages/aphrodite/modeling/model_loader/loader.py", line 167, in _initialize_model
return build_model(
File "/home/carlosfm/kalavai/kalavai-client/templates/aphrodite/env/lib/python3.10/site-packages/aphrodite/modeling/model_loader/loader.py", line 152, in build_model
return model_class(config=hf_config,
File "/home/carlosfm/kalavai/kalavai-client/templates/aphrodite/env/lib/python3.10/site-packages/aphrodite/modeling/models/llama.py", line 427, in __init__
self.lm_head.weight = self.model.embed_tokens.weight
File "/home/carlosfm/kalavai/kalavai-client/templates/aphrodite/env/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1729, in __getattr__
raise AttributeError(f"'{type(self).__name__}' object has no attribute '{name}'")
AttributeError: 'VocabParallelEmbedding' object has no attribute 'weight'. Did you mean: 'qweight'?
Phi-3.5-mini-instruct-IQ2_M.gguf from bartowski/Phi-3.5-mini-instruct-GGUF
INFO: Loading model Phi-3.5-mini-instruct-IQ2_M.gguf...
⠋ Loading modules... ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 4/325 1% 0:00:00
Process SpawnProcess-1:
Traceback (most recent call last):
File "/usr/lib/python3.10/multiprocessing/process.py", line 314, in _bootstrap
self.run()
File "/usr/lib/python3.10/multiprocessing/process.py", line 108, in run
self._target(*self._args, **self._kwargs)
File "/home/carlosfm/kalavai/kalavai-client/templates/aphrodite/env/lib/python3.10/site-packages/aphrodite/endpoints/openai/rpc/server.py", line 209, in run_rpc_server
server = AsyncEngineRPCServer(async_engine_args, rpc_path)
File "/home/carlosfm/kalavai/kalavai-client/templates/aphrodite/env/lib/python3.10/site-packages/aphrodite/endpoints/openai/rpc/server.py", line 24, in __init__
self.engine = AsyncAphrodite.from_engine_args(async_engine_args)
File "/home/carlosfm/kalavai/kalavai-client/templates/aphrodite/env/lib/python3.10/site-packages/aphrodite/engine/async_aphrodite.py", line 601, in from_engine_args
engine = cls(
File "/home/carlosfm/kalavai/kalavai-client/templates/aphrodite/env/lib/python3.10/site-packages/aphrodite/engine/async_aphrodite.py", line 510, in __init__
self.engine = self._init_engine(*args, **kwargs)
File "/home/carlosfm/kalavai/kalavai-client/templates/aphrodite/env/lib/python3.10/site-packages/aphrodite/engine/async_aphrodite.py", line 694, in _init_engine
return engine_class(*args, **kwargs)
File "/home/carlosfm/kalavai/kalavai-client/templates/aphrodite/env/lib/python3.10/site-packages/aphrodite/engine/aphrodite_engine.py", line 261, in __init__
self.model_executor = executor_class(
File "/home/carlosfm/kalavai/kalavai-client/templates/aphrodite/env/lib/python3.10/site-packages/aphrodite/executor/executor_base.py", line 45, in __init__
self._init_executor()
File "/home/carlosfm/kalavai/kalavai-client/templates/aphrodite/env/lib/python3.10/site-packages/aphrodite/executor/gpu_executor.py", line 36, in _init_executor
self.driver_worker.load_model()
File "/home/carlosfm/kalavai/kalavai-client/templates/aphrodite/env/lib/python3.10/site-packages/aphrodite/task_handler/worker.py", line 153, in load_model
self.model_runner.load_model()
File "/home/carlosfm/kalavai/kalavai-client/templates/aphrodite/env/lib/python3.10/site-packages/aphrodite/task_handler/model_runner.py", line 888, in load_model
self.model = get_model(model_config=self.model_config,
File "/home/carlosfm/kalavai/kalavai-client/templates/aphrodite/env/lib/python3.10/site-packages/aphrodite/modeling/model_loader/__init__.py", line 20, in get_model
return loader.load_model(model_config=model_config,
File "/home/carlosfm/kalavai/kalavai-client/templates/aphrodite/env/lib/python3.10/site-packages/aphrodite/modeling/model_loader/loader.py", line 1035, in load_model
model.load_weights(
File "/home/carlosfm/kalavai/kalavai-client/templates/aphrodite/env/lib/python3.10/site-packages/aphrodite/modeling/models/llama.py", line 544, in load_weights
weight_loader(param, loaded_weight)
File "/home/carlosfm/kalavai/kalavai-client/templates/aphrodite/env/lib/python3.10/site-packages/aphrodite/modeling/layers/linear.py", line 832, in weight_loader
assert param_data.shape == loaded_weight.shape
AssertionError
I am running into the same issue with Llama3.2-3B-Instruct.Q4_K_M.gguf (getting AttributeError: 'VocabParallelEmbedding' object has no attribute 'weight'). For what its worth, I was getting this exact error with an older version of vllm, but it was resolved once I updated to the latest vllm version. Any help would be much appreciated, thanks.
This issue has been fixed on the latest main. There are no releases for it yet (and likely won't be on PyPi for a while, due to their wheel size restrictions), but you can build from source.
due to their wheel size restrictions
They made an exception for pytorch https://github.com/pypa/packaging-problems/issues/96
due to their wheel size restrictions
They made an exception for pytorch pypa/packaging-problems#96
We requested an extension before at pypi/support#4036, and it was approved. But since then, our wheel sizes have exceeded even torch's, at close to 1GiB. We've requested another extension at pypi/support#5552, but are yet to hear anything back.