[NVIDIA] Upgrade vLLM to v0.11.2#273
Merged
Merged
Conversation
Updated configs: - Use FP8 kv-cache for GPT-OSS B200. - Remove "custom_ops" from compilation-config for GPT-OSS. - Remove "cudagraph_mode" from compilation-config for GPT-OSS. - Remove VLLM_FLASHINFER_ALLREDUCE_FUSION_THRESHOLDS_MB env var for GPT-OSS. - Remove deprecated "--disable-log-requests" flag. - Rename "cuda-graph-sizes" flag. Signed-off-by: Po-Han Huang <pohanh@nvidia.com>
Collaborator
|
vLLM releasin too fast @mgoin we can't keep up |
functionstackx
temporarily deployed
to
fork-pr-validation
GitHub Actions
Inactive
functionstackx
temporarily deployed
to
fork-pr-validation
GitHub Actions
Inactive
cquil11
temporarily deployed
to
fork-pr-validation
GitHub Actions
Inactive
Collaborator
|
@ankursingh-nv is this ready to go once the checks pass? |
cquil11
temporarily deployed
to
fork-pr-validation
GitHub Actions
Inactive
Contributor
Author
|
@cquil11 should be ready once we get a successful E2E run. Currently some h100 and h200 jobs are failing (refer https://github.com/InferenceMAX/InferenceMAX/actions/runs/19904064308) |
Collaborator
|
@ankursingh-nv with vllm 0.11.2 it seems vllm server process attempts to write to host fs, so I added |
Contributor
Author
|
@cquil11 interesting. |
Collaborator
cquil11
reviewed
Dec 5, 2025
cquil11
reviewed
Dec 5, 2025
cquil11
reviewed
Dec 5, 2025
cquil11
reviewed
Dec 5, 2025
Collaborator
|
@Oseltamivir + viz |
functionstackx
temporarily deployed
to
fork-pr-validation
GitHub Actions
Inactive
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
4 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Updated configs:
Test sweep: https://github.com/InferenceMAX/InferenceMAX/actions/runs/19946962635