16 lines
446 B
Plaintext
16 lines
446 B
Plaintext
ninja # For faster builds.
|
|
psutil
|
|
ray >= 2.9
|
|
sentencepiece # Required for LLaMA tokenizer.
|
|
numpy
|
|
torch == 2.1.2
|
|
transformers >= 4.37.0 # Required for Qwen2
|
|
xformers == 0.0.23.post1 # Required for CUDA 12.1.
|
|
fastapi
|
|
uvicorn[standard]
|
|
pydantic >= 2.0 # Required for OpenAI server.
|
|
aioprometheus[starlette]
|
|
pynvml == 11.5.0
|
|
triton >= 2.1.0
|
|
cupy-cuda12x == 12.3.0 # Required for CUDA graphs. CUDA 11.8 users should install cupy-cuda11x instead.
|