Skip to content

Conversation

hmellor
Copy link
Member

@hmellor hmellor commented Apr 17, 2025

Follows #16332, #16422, #16533, #16603

Notable changes:

  • --limit-mm-per-prompt moves away from the custom nullable_kvs type in preference to JSON strings (which are used for all other mapping inputs)
  • The nullable_kvs will still work as a fallback with a warning during the transition period

hmellor added 3 commits April 17, 2025 16:11
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
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.

🚀

@mergify mergify bot added documentation Improvements or additions to documentation multi-modality Related to multi-modality (#4194) labels Apr 17, 2025
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
args = [
"--dtype=bfloat16", "--max-model-len=4096", "--enforce-eager",
f'--limit-mm-per-prompt={{"audio":{len(audio_assets)}}}',
"--trust-remote-code"
f"--limit-mm-per-prompt='{limit_mm_per_prompt}'", "--trust-remote-code"
Copy link
Member

Choose a reason for hiding this comment

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

Separate the arguments

Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
@DarkLight1337 DarkLight1337 enabled auto-merge (squash) April 17, 2025 16:23
@github-actions github-actions bot added the ready ONLY add when PR is ready to merge/full CI is needed label Apr 17, 2025
@vllm-bot vllm-bot merged commit e78587a into vllm-project:main Apr 18, 2025
47 of 52 checks passed
@hmellor hmellor changed the title Improve-mm-and-pooler-and-decoding-configs Improve configs - MultiModalConfig + PoolerConfig + DecodingConfig Apr 18, 2025
@hmellor hmellor deleted the improve-mm-and-pooler-and-decoding-configs branch April 18, 2025 10:27
yangw-dev pushed a commit to yangw-dev/vllm that referenced this pull request Apr 21, 2025
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Signed-off-by: Yang Wang <elainewy@meta.com>
jikunshang pushed a commit to jikunshang/vllm that referenced this pull request Apr 29, 2025
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
lk-chen pushed a commit to lk-chen/vllm that referenced this pull request Apr 29, 2025
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
adobrzyn pushed a commit to HabanaAI/vllm-fork that referenced this pull request Apr 30, 2025
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Signed-off-by: Agata Dobrzyniewicz <adobrzyniewicz@habana.ai>
RichardoMrMu pushed a commit to RichardoMrMu/vllm that referenced this pull request May 12, 2025
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Signed-off-by: Mu Huai <tianbowen.tbw@antgroup.com>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
documentation Improvements or additions to documentation multi-modality Related to multi-modality (#4194) ready ONLY add when PR is ready to merge/full CI is needed
Projects
None yet
Development

Successfully merging this pull request may close these issues.

3 participants