@tduncan / Nvidia-Optimization-Stack-VLLM Mirror · read-only / commits / 6f32cddf1c
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, 04:15 UTC

Remove Flash Attention in test env (#2982)

Woosuk Kwon committed Feb 22, 2024 at 09:58 UTC 6f32cddf1c795e74a47e84620462431154718f49
1 file changed +1 -2
requirements-dev.txt
+1 -2
@@ -17,7 +17,6 @@ pytest-forked
17 pytest-asyncio
18 httpx
19 einops # required for MPT
20 -flash_attn # required for HuggingFace's llama implementation
20 openai
21 requests
23 -ray
\ No newline at end of file
22 +ray