Skip to content

Upgrade FlashInfer to v0.2.11 #22613

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
Aug 12, 2025
Merged

Upgrade FlashInfer to v0.2.11 #22613

merged 2 commits into from
Aug 12, 2025
+2 −2

Conversation

nvpohanh
Copy link
Contributor

@nvpohanh nvpohanh commented Aug 11, 2025 •
edited by github-actions bot
Loading

This includes the fix needed for FlashInfer AOT compilation failures. See: flashinfer-ai/flashinfer#1403 and flashinfer-ai/flashinfer#1410

Essential Elements of an Effective PR Description Checklist

  • The purpose of the PR, such as "Fix some issue (link existing issues this PR will resolve)".
  • The test plan, such as providing test command.
  • The test results, such as pasting the results comparison before and after, or e2e results
  • (Optional) The necessary documentation update, such as updating supported_models.md and examples for a new model.

Purpose

Test Plan

Llama 4 Scout FP8/FP4 accuracy

Test Result

Llama 4 Scout FP8 accuracy

local-completions (base_url=http://0.0.0.0:8080/v1/completions,model=nvidia/Llama-4-Scout-17B-16E-Instruct-FP8,tokenized_requests=False,tokenizer_backend=None,num_concurrent=128,timeout=120,max_retries=5), gen_kwargs: (None), limit: None, num_fewshot: None, batch_size: 1
|Tasks|Version|     Filter     |n-shot|  Metric   |   |Value |   |Stderr|
|-----|------:|----------------|-----:|-----------|---|-----:|---|-----:|
|gsm8k|      3|flexible-extract|     5|exact_match|↑  |0.9121|±  |0.0078|
|     |       |strict-match    |     5|exact_match|↑  |0.8946|±  |0.0085|

Llama 4 Scout FP4 accuracy (using this PR plus #22511 )

local-completions (base_url=http://0.0.0.0:8080/v1/completions,model=nvidia/Llama-4-Scout-17B-16E-Instruct-FP4,tokenized_requests=False,tokenizer_backend=None,num_concurrent=128,timeout=120,max_retries=5), gen_kwargs: (None), limit: None, num_fewshot: None, batch_size: 1
|Tasks|Version|     Filter     |n-shot|  Metric   |   |Value |   |Stderr|
|-----|------:|----------------|-----:|-----------|---|-----:|---|-----:|
|gsm8k|      3|flexible-extract|     5|exact_match|↑  |0.9060|±  |0.0080|
|     |       |strict-match    |     5|exact_match|↑  |0.8901|±  |0.0086|

(Optional) Documentation Update

@nvpohanh
Upgrade FlashInfer to v0.2.11
cc46f56 
This includes the fix needed for FlashInfer AOT compilation failures.
See: flashinfer-ai/flashinfer#1403 and
flashinfer-ai/flashinfer#1410

Signed-off-by: Po-Han Huang <[email protected]>
@mergify mergify bot added the ci/build label Aug 11, 2025
gemini-code-assist[bot]
gemini-code-assist bot reviewed Aug 11, 2025
View reviewed changes
Copy link
Contributor

@gemini-code-assist gemini-code-assist bot left a comment

Choose a reason for hiding this comment

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

Code Review

This pull request upgrades FlashInfer to version v0.2.11. The version is updated consistently in both docker/Dockerfile for the source build and in setup.py for the package dependency. This change is intended to resolve AOT compilation failures, and the provided test results show that model accuracy is maintained. The changes are correct and align with the goal of the pull request.

@github-actions 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.

🚀

@mgoin mgoin added the ready ONLY add when PR is ready to merge/full CI is needed label Aug 11, 2025
@mgoin mgoin enabled auto-merge (squash) August 11, 2025 23:13
@vllm-bot vllm-bot merged commit dc5e4a6 into vllm-project:main Aug 12, 2025
70 of 75 checks passed
aarnphm pushed a commit to aarnphm/vllm that referenced this pull request Aug 13, 2025
@nvpohanh @mgoin @aarnphm
Upgrade FlashInfer to v0.2.11 (vllm-project#22613)
85e16d9 
Signed-off-by: Po-Han Huang <[email protected]>
Co-authored-by: mgoin <[email protected]>
paulpak58 pushed a commit to paulpak58/vllm that referenced this pull request Aug 13, 2025
@nvpohanh @mgoin @paulpak58
Upgrade FlashInfer to v0.2.11 (vllm-project#22613)
2fb8972 
Signed-off-by: Po-Han Huang <[email protected]>
Co-authored-by: mgoin <[email protected]>
Signed-off-by: Paul Pak <[email protected]>
taneem-ibrahim pushed a commit to taneem-ibrahim/vllm that referenced this pull request Aug 14, 2025
@nvpohanh @mgoin @taneem-ibrahim
Upgrade FlashInfer to v0.2.11 (vllm-project#22613)
e9856b2 
Signed-off-by: Po-Han Huang <[email protected]>
Co-authored-by: mgoin <[email protected]>
BoyuanFeng pushed a commit to BoyuanFeng/vllm that referenced this pull request Aug 14, 2025
@nvpohanh @mgoin @BoyuanFeng
Upgrade FlashInfer to v0.2.11 (vllm-project#22613)
6e28f9f 
Signed-off-by: Po-Han Huang <[email protected]>
Co-authored-by: mgoin <[email protected]>
Signed-off-by: Boyuan Feng <[email protected]>
diegocastanibm pushed a commit to diegocastanibm/vllm that referenced this pull request Aug 15, 2025
@nvpohanh @mgoin @diegocastanibm
Upgrade FlashInfer to v0.2.11 (vllm-project#22613)
02cc1af 
Signed-off-by: Po-Han Huang <[email protected]>
Co-authored-by: mgoin <[email protected]>
Signed-off-by: Diego-Castan <[email protected]>
juuice-lee pushed a commit to juuice-lee/vllm-moe.code that referenced this pull request Aug 18, 2025
@nvpohanh @mgoin
Upgrade FlashInfer to v0.2.11 (vllm-project#22613)
aa76b1f 
Signed-off-by: Po-Han Huang <[email protected]>
Co-authored-by: mgoin <[email protected]>
yiliu30 pushed a commit to yiliu30/vllm-fork that referenced this pull request Aug 19, 2025
@nvpohanh @mgoin @yiliu30
Upgrade FlashInfer to v0.2.11 (vllm-project#22613)
b7ee5b3 
Signed-off-by: Po-Han Huang <[email protected]>
Co-authored-by: mgoin <[email protected]>
epwalsh pushed a commit to epwalsh/vllm that referenced this pull request Aug 28, 2025
@nvpohanh @mgoin @epwalsh
Upgrade FlashInfer to v0.2.11 (vllm-project#22613)
03c721a 
Signed-off-by: Po-Han Huang <[email protected]>
Co-authored-by: mgoin <[email protected]>
xiao-llm pushed a commit to xiao-llm/vllm that referenced this pull request Aug 28, 2025
@nvpohanh @mgoin @amd-xiaoyu12
Upgrade FlashInfer to v0.2.11 (vllm-project#22613)
42ae0e1 
Signed-off-by: Po-Han Huang <[email protected]>
Co-authored-by: mgoin <[email protected]>
Signed-off-by: Xiao Yu <[email protected]>
xiao-llm pushed a commit to xiao-llm/vllm that referenced this pull request Aug 28, 2025
@nvpohanh @mgoin @amd-xiaoyu12
Upgrade FlashInfer to v0.2.11 (vllm-project#22613)
9c45ff3 
Signed-off-by: Po-Han Huang <[email protected]>
Co-authored-by: mgoin <[email protected]>
Signed-off-by: Xiao Yu <[email protected]>
zhewenl pushed a commit to zhewenl/vllm that referenced this pull request Aug 28, 2025
@nvpohanh @mgoin @zhewenl
Upgrade FlashInfer to v0.2.11 (vllm-project#22613)
d6b4963 
Signed-off-by: Po-Han Huang <[email protected]>
Co-authored-by: mgoin <[email protected]>
dumb0002 pushed a commit to dumb0002/vllm that referenced this pull request Aug 28, 2025
@nvpohanh @mgoin @dumb0002
Upgrade FlashInfer to v0.2.11 (vllm-project#22613)
295338d 
Signed-off-by: Po-Han Huang <[email protected]>
Co-authored-by: mgoin <[email protected]>
googlercolin pushed a commit to googlercolin/vllm that referenced this pull request Aug 29, 2025
@nvpohanh @mgoin @googlercolin
Upgrade FlashInfer to v0.2.11 (vllm-project#22613)
358986f 
Signed-off-by: Po-Han Huang <[email protected]>
Co-authored-by: mgoin <[email protected]>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@mgoin mgoin mgoin approved these changes

+1 more reviewer

@gemini-code-assist gemini-code-assist[bot] gemini-code-assist[bot] left review comments

Reviewers whose approvals may not affect merge requirements
Assignees
No one assigned
Labels
ci/build ready ONLY add when PR is ready to merge/full CI is needed
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
3 participants
@nvpohanh @mgoin @vllm-bot