llama.cpp-prismml / requirements /requirements-tool_bench.txt
OpenTransformer's picture
Q1_0_g128 CPU kernel fix + AVX2 SIMD (fork of PrismML-Eng/llama.cpp)
03ba2cd verified
aiohttp~=3.9.3
pytest~=8.3.3
huggingface_hub>=0.34.0,<1.0
matplotlib~=3.10.0
numpy~=1.26.4
openai~=2.14.0
pandas~=2.2.3
prometheus-client~=0.20.0
requests~=2.32.3
wget~=3.2
typer~=0.15.1
seaborn~=0.13.2