Skip to content

[ROCm] [AITER] [Bugfix] Patch for AITER commit 648764942e552a8bb5fe16026703716a81f05374 #18990

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 2 commits into from
Jun 19, 2025
Merged

[ROCm] [AITER] [Bugfix] Patch for AITER commit 648764942e552a8bb5fe16026703716a81f05374 #18990

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
6cf31ef
new aiter commit introduced new enum
tjtanaa May 31, 2025
e0b7db1
upgrade aiter commit
tjtanaa Jun 2, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion docker/Dockerfile.rocm_base
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -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="c1debd8"
ARG AITER_BRANCH="6487649"
ARG AITER_REPO="https://github.com/ROCm/aiter.git"

FROM ${BASE_IMAGE} AS base
Expand Down
5 changes: 3 additions & 2 deletions vllm/model_executor/layers/fused_moe/rocm_aiter_fused_moe.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -21,8 +21,9 @@ class QuantMethod(IntEnum):
NO = 0 # a16w16
PER_TENSOR = 1 # w8a8 (pre_Tensor)
PER_TOKEN = 2 # w8a8/w8a4 (per_Token)
BLOCK_1X128 = 3 # block quantized w8a8 (per_1x128)
BLOCK_128x128 = 4 # block quantized w8a8 (per_128x128)
BLOCK_1X32 = 3 # fp4x2
BLOCK_1X128 = 4 # block quantized w8a8 (per_1x128)
BLOCK_128x128 = 5 # block quantized w8a8 (per_128x128)


class ActivationMethod(IntEnum):
Expand Down