@tduncan / Nvidia-Optimization-Stack-VLLM Mirror · read-only / commits / 7e1b21daac
Fork 0

A high-throughput and memory-efficient inference and serving engine for LLMs

Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git

Synced Nov 17, 05:30 UTC

Remove einops from requirements (#2049)

Woosuk Kwon committed Dec 12, 2023 at 09:34 UTC 7e1b21daacaedb18a7001a4f5990d992209c4f78
2 files changed -2
requirements-rocm.txt
-1
@@ -9,7 +9,6 @@ sentencepiece # Required for LLaMA tokenizer.
9 numpy
10 tokenizers>=0.15.0
11 huggingface_hub<0.18,>=0.16.4
12 -einops # Required for phi-1_5
12 transformers >= 4.36.0 # Required for Mixtral.
13 fastapi
14 uvicorn[standard]
requirements.txt
-1
@@ -5,7 +5,6 @@ pandas # Required for Ray data.
5 pyarrow # Required for Ray data.
6 sentencepiece # Required for LLaMA tokenizer.
7 numpy
8 -einops # Required for phi-1_5
8 torch >= 2.1.1
9 transformers >= 4.36.0 # Required for Mixtral.
10 xformers >= 0.0.23 # Required for CUDA 12.1.