biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

[FEAT][ROCm] Integrate Paged Attention Kernel from AITER (#15001)

Browse Source 
Signed-off-by: vllmellm <vllm.ellm@embeddedllm.com>
Signed-off-by: tjtanaa <tunjian.tan@embeddedllm.com>
Co-authored-by: tjtanaa <tunjian.tan@embeddedllm.com>
This commit is contained in:
vllmellm
2025-04-22 17:46:28 +08:00
committed by GitHub
parent 8f7bace7c3
commit 0e237f0035
5 changed files with 195 additions and 27 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
docker/Dockerfile.rocm_base
View File

@@ -12,7 +12,7 @@ ARG PYTORCH_REPO="https://github.com/pytorch/pytorch.git"
ARG PYTORCH_VISION_REPO="https://github.com/pytorch/vision.git"
ARG FA_BRANCH="1a7f4dfa"
ARG FA_REPO="https://github.com/Dao-AILab/flash-attention.git"
ARG AITER_BRANCH="5a77249"
ARG AITER_BRANCH="7e1ed08"
ARG AITER_REPO="https://github.com/ROCm/aiter.git"
FROM ${BASE_IMAGE} AS base