Skip to content

[AMD] ENV Flags tuning and cleanup #19176

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
HaiShaw merged 1 commit into from
Feb 23, 2026
Merged

[AMD] ENV Flags tuning and cleanup #19176

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
5 changes: 1 addition & 4 deletions docker/rocm.Dockerfile
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -390,10 +390,7 @@ ENV SGLANG_USE_AITER=1
ENV SGLANG_USE_ROCM700A=1

ENV NCCL_MIN_NCHANNELS=112
ENV VLLM_FP8_PADDING=1
ENV VLLM_FP8_ACT_PADDING=1
ENV VLLM_FP8_WEIGHT_PADDING=1
ENV VLLM_FP8_REDUCE_CONV=1
ENV ROCM_QUICK_REDUCE_QUANTIZATION=INT8
Copy link
Copy Markdown
Contributor

@gemini-code-assist gemini-code-assist bot Feb 23, 2026

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

medium

Enabling ROCM_QUICK_REDUCE_QUANTIZATION=INT8 by default could have performance and accuracy implications that might be unexpected for users. It's good practice to document such impactful settings. Please consider adding a comment to explain this environment variable.

ENV ROCM_QUICK_REDUCE_QUANTIZATION=INT8 # Enable INT8 quantization for quick all-reduce on ROCm. Other values: FP, INT6, INT4, NONE.

ENV TORCHINDUCTOR_MAX_AUTOTUNE=1
ENV TORCHINDUCTOR_MAX_AUTOTUNE_POINTWISE=1

Expand Down
5 changes: 1 addition & 4 deletions docker/rocm720.Dockerfile
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -496,10 +496,7 @@ ENV SGLANG_USE_AITER=1
ENV SGLANG_USE_ROCM700A=1

ENV NCCL_MIN_NCHANNELS=112
ENV VLLM_FP8_PADDING=1
ENV VLLM_FP8_ACT_PADDING=1
ENV VLLM_FP8_WEIGHT_PADDING=1
ENV VLLM_FP8_REDUCE_CONV=1
ENV ROCM_QUICK_REDUCE_QUANTIZATION=INT8
Copy link
Copy Markdown
Contributor

@gemini-code-assist gemini-code-assist bot Feb 23, 2026

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

medium

Enabling ROCM_QUICK_REDUCE_QUANTIZATION=INT8 by default could have performance and accuracy implications that might be unexpected for users. It's good practice to document such impactful settings. Please consider adding a comment to explain this environment variable.

ENV ROCM_QUICK_REDUCE_QUANTIZATION=INT8 # Enable INT8 quantization for quick all-reduce on ROCm. Other values: FP, INT6, INT4, NONE.

ENV TORCHINDUCTOR_MAX_AUTOTUNE=1
ENV TORCHINDUCTOR_MAX_AUTOTUNE_POINTWISE=1

Expand Down
Loading