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

Jump to bottom
Merged
merged 2 commits into from
Jun 19, 2025
Merged

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

merged 2 commits into from
Jun 19, 2025

Conversation

@tjtanaa
Copy link
Contributor

@tjtanaa tjtanaa commented May 31, 2025 •
edited by github-actions bot
Loading

This PR is a bugfix after PR (#18596). ONLY Merge this after PR (#18596).

This PR also include upgrading the AITER commit of the Dockerfile.

PR (#18596) introduced the use of AITER MHA which depends on a new AITER commit 648764942e552a8bb5fe16026703716a81f05374.

AITER commit: ROCm/aiter@a02a93d has introduced a new enum value in a breaking changes manner.

lm_eval after fix

Qwen/Qwen3-235B-A22B-FP8

vllm (pretrained=Qwen/Qwen3-235B-A22B-FP8,tensor_parallel_size=2,max_model_len=10000,trust_remote_code=True), gen_kwargs: (None), limit: None, num_fewshot: 5, batch_size: auto
|Tasks|Version|     Filter     |n-shot|  Metric   |   |Value |   |Stderr|
|-----|------:|----------------|-----:|-----------|---|-----:|---|-----:|
|gsm8k|      3|flexible-extract|     5|exact_match|↑  |0.8613|±  |0.0095|
|     |       |strict-match    |     5|exact_match|↑  |0.8408|±  |0.0101|

mistralai/Mixtral-8x7B-Instruct-v0.1

vllm (pretrained=mistralai/Mixtral-8x7B-Instruct-v0.1,tensor_parallel_size=2,max_model_len=10000,trust_remote_code=True), gen_kwargs: (None), limit: None, num_fewshot: 5, batch_size: auto
|Tasks|Version|     Filter     |n-shot|  Metric   |   |Value |   |Stderr|
|-----|------:|----------------|-----:|-----------|---|-----:|---|-----:|
|gsm8k|      3|flexible-extract|     5|exact_match|↑  |0.6399|±  |0.0132|
|     |       |strict-match    |     5|exact_match|↑  |0.6361|±  |0.0133|

mistralai/Mixtral-8x7B-Instruct-v0.1 dynamic fp8 quantization

vllm (pretrained=mistralai/Mixtral-8x7B-Instruct-v0.1,tensor_parallel_size=2,quantization=fp8,max_model_len=10000,trust_remote_code=True), gen_kwargs: (None), limit: None, num_fewshot: 5, batch_size: auto
|Tasks|Version|     Filter     |n-shot|  Metric   |   |Value |   |Stderr|
|-----|------:|----------------|-----:|-----------|---|-----:|---|-----:|
|gsm8k|      3|flexible-extract|     5|exact_match|↑  |0.5777|±  |0.0136|
|     |       |strict-match    |     5|exact_match|↑  |0.5754|±  |0.0136|

deepseek-ai/DeepSeek-V3

vllm (pretrained=deepseek-ai/DeepSeek-V3,tensor_parallel_size=8,block_size=1,trust_remote_code=True), gen_kwargs: (None), limit: None, num_fewshot: 5, batch_size: auto
|Tasks|Version|     Filter     |n-shot|  Metric   |   |Value |   |Stderr|
|-----|------:|----------------|-----:|-----------|---|-----:|---|-----:|
|gsm8k|      3|flexible-extract|     5|exact_match|↑  |0.9454|±  |0.0063|
|     |       |strict-match    |     5|exact_match|↑  |0.9454|±  |0.0063|

Note:
Even if the AITER commit: 648764942e552a8bb5fe16026703716a81f05374 introduced a new input argument min_seqlen_q to flash_attn_varlen_func. It seems that the default value is set to 0 which retains compatibility with how the MHA is used in the ROCm MLA v1 class. Refer to https://github.com/ROCm/aiter/blob/2c1a21adad9c5b5e02619c7dd05d63f9afda3642/aiter/ops/mha.py#L1369

@github-actions
Copy link

👋 Hi! Thank you for contributing to the vLLM project.

💬 Join our developer Slack at https://slack.vllm.ai to discuss your PR in #pr-reviews, coordinate on features in #feat- channels, or join special interest groups in #sig- channels.

Just a reminder: PRs would not trigger full CI run by default. Instead, it would only run fastcheck CI which starts running only a small and essential subset of CI tests to quickly catch errors. You can run other CI tests on top of those by going to your fastcheck build on Buildkite UI (linked in the PR checks section) and unblock them. If you do not have permission to unblock, ping simon-mo or khluu to add you in our Buildkite org.

Once the PR is approved and ready to go, your PR reviewer(s) can run CI to test the changes comprehensively before merging.

To run CI, PR reviewers can either: Add ready label to the PR or enable auto-merge.

🚀

@tjtanaa tjtanaa mentioned this pull request May 31, 2025
Merged
@houseroad
Copy link
Collaborator

cc: @842974287

@tjtanaa tjtanaa marked this pull request as ready for review June 2, 2025 07:35
@tjtanaa tjtanaa mentioned this pull request Jun 2, 2025
Open
61 tasks
@tjtanaa
upgrade aiter commit
e0b7db1 
Signed-off-by: tjtanaa <[email protected]>
@mergify mergify bot added the ci/build label Jun 2, 2025
@xuechenwang-cienet xuechenwang-cienet mentioned this pull request Jun 4, 2025
Closed
1 task
@mergify mergify bot added the rocm Related to AMD ROCm label Jun 13, 2025
@gshtras gshtras mentioned this pull request Jun 17, 2025
Closed
@mergify mergify bot added the qwen Related to Qwen models label Jun 18, 2025
@tjtanaa
Copy link
Contributor Author

tjtanaa commented Jun 18, 2025

@houseroad
The PR #18596 has been merged. Could we try to proceed with this PR to make fixes so that AITER fused moe kernel could run with this new AITER commit?

@DarkLight1337 DarkLight1337 enabled auto-merge (squash) June 19, 2025 02:48
@github-actions github-actions bot added the ready ONLY add when PR is ready to merge/full CI is needed label Jun 19, 2025
@DarkLight1337 DarkLight1337 added force-merge and removed force-merge qwen Related to Qwen models labels Jun 19, 2025
@vllm-bot vllm-bot merged commit 2de12be into vllm-project:main Jun 19, 2025
66 of 69 checks passed
@mergify mergify bot added the qwen Related to Qwen models label Jun 19, 2025
@vllmellm vllmellm mentioned this pull request Aug 26, 2025
Open
61 tasks
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Reviewers

@DarkLight1337 DarkLight1337 DarkLight1337 approved these changes

Assignees

No one assigned

Labels

ci/build qwen Related to Qwen models ready ONLY add when PR is ready to merge/full CI is needed rocm Related to AMD ROCm

Projects

None yet

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

4 participants

@tjtanaa @houseroad @DarkLight1337 @vllm-bot