Llama.cpp running twice when it is run alone

[lolxdmainkaisemaanlu]

siddhesh@desktop:~/Desktop$ langflow [18:57:38] INFO [18:57:38] - INFO - Logger set up with log logger.py:28 level: 20(info)
INFO [18:57:38] - INFO - Log file: logs/langflow.log logger.py:30 [2023-04-26 18:57:38 +0530] [38894] [INFO] Starting gunicorn 20.1.0 [2023-04-26 18:57:38 +0530] [38894] [INFO] Listening at: http://127.0.0.1:7860 (38894) [2023-04-26 18:57:38 +0530] [38894] [INFO] Using worker: uvicorn.workers.UvicornWorker [2023-04-26 18:57:38 +0530] [38906] [INFO] Booting worker with pid: 38906 [2023-04-26 18:57:38 +0530] [38906] [INFO] Started server process [38906] [2023-04-26 18:57:38 +0530] [38906] [INFO] Waiting for application startup. [2023-04-26 18:57:38 +0530] [38906] [INFO] Application startup complete. llama_model_load: loading model from '/home/siddhesh/Desktop/vicuna.bin' - please wait ... llama_model_load: n_vocab = 32001 llama_model_load: n_ctx = 512 llama_model_load: n_embd = 4096 llama_model_load: n_mult = 256 llama_model_load: n_head = 32 llama_model_load: n_layer = 32 llama_model_load: n_rot = 128 llama_model_load: f16 = 2 llama_model_load: n_ff = 11008 llama_model_load: n_parts = 1 llama_model_load: type = 1 llama_model_load: ggml map size = 4017.70 MB llama_model_load: ggml ctx size = 81.25 KB llama_model_load: mem required = 5809.78 MB (+ 2052.00 MB per state) llama_model_load: loading tensors from '/home/siddhesh/Desktop/vicuna.bin' llama_model_load: model size = 4017.27 MB / num tensors = 291 llama_init_from_file: kv self size = 512.00 MB AVX = 1 | AVX2 = 1 | AVX512 = 0 | FMA = 1 | NEON = 0 | ARM_FMA = 0 | F16C = 1 | FP16_VA = 0 | WASM_SIMD = 0 | BLAS = 0 | SSE3 = 1 | VSX = 0 | llama_model_load: loading model from '/home/siddhesh/Desktop/vicuna.bin' - please wait ... llama_model_load: n_vocab = 32001 llama_model_load: n_ctx = 512 llama_model_load: n_embd = 4096 llama_model_load: n_mult = 256 llama_model_load: n_head = 32 llama_model_load: n_layer = 32 llama_model_load: n_rot = 128 llama_model_load: f16 = 2 llama_model_load: n_ff = 11008 llama_model_load: n_parts = 1 llama_model_load: type = 1 llama_model_load: ggml map size = 4017.70 MB llama_model_load: ggml ctx size = 81.25 KB llama_model_load: mem required = 5809.78 MB (+ 2052.00 MB per state) llama_model_load: loading tensors from '/home/siddhesh/Desktop/vicuna.bin' llama_model_load: model size = 4017.27 MB / num tensors = 291 llama_init_from_file: kv self size = 512.00 MB AVX = 1 | AVX2 = 1 | AVX512 = 0 | FMA = 1 | NEON = 0 | ARM_FMA = 0 | F16C = 1 | FP16_VA = 0 | WASM_SIMD = 0 | BLAS = 0 | SSE3 = 1 | VSX = 0 | [2023-04-26 18:59:20 +0530] [38894] [INFO] Handling signal: winch

llama_print_timings: load time = 1667.92 ms llama_print_timings: sample time = 48.17 ms / 128 runs ( 0.38 ms per run) llama_print_timings: prompt eval time = 1667.88 ms / 8 tokens ( 208.48 ms per token) llama_print_timings: eval time = 16544.15 ms / 127 runs ( 130.27 ms per run) llama_print_timings: total time = 18273.72 ms

It looks like it tries to load the first time and is unsuccessful but runs the second time. This happens everytime.

[ogabrielluiz]

Interesting. I haven't been able to test it thoroughly yet. Could you elaborate? When does that happen?

[ogabrielluiz]

Interesting. I haven't been able to test it thoroughly yet. Could you elaborate? When does that happen?

[alexfilothodoros]

Hi,

I have this problem as well, just by running llama.cpp. I don't think it's a langflow issue.

[stale[bot]]

This issue has been automatically marked as stale because it has not had recent activity. It will be closed if no further activity occurs. Thank you for your contributions.