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.