[rollout] chore: bump up trtllm image version to 1.3.0rc10#5841
Open
Superjomn wants to merge 23 commits intoverl-project:mainfrom
Open
[rollout] chore: bump up trtllm image version to 1.3.0rc10#5841Superjomn wants to merge 23 commits intoverl-project:mainfrom
Superjomn wants to merge 23 commits intoverl-project:mainfrom
Conversation
![gemini-code-assist[bot]](https://avatars.githubusercontent.com/in/956858?s=60&v=4){kind=small}
Contributor
There was a problem hiding this comment.
Code Review
This pull request updates the TRT-LLM rollout implementation and Docker environment, including upgrading Megatron-LM to v0.16.0 and transitioning to SleepConfig for server management. It also removes the single-node restriction for TRT-LLM replicas. Review feedback points out that using a branch name for the DeepEP dependency in the Dockerfile compromises build reproducibility and identifies a potential IndexError in the placement group indexing logic that requires a bounds check.
Collaborator
|
Should we also bump ci image? |
8 tasks
hchings
reviewed
Apr 2, 2026
Superjomn
changed the title
Superjomn
changed the title
Superjomn
changed the title
hchings
approved these changes
Apr 3, 2026
Collaborator
hchings
left a comment
hchings
left a comment
There was a problem hiding this comment.
Please address the cherry-pick comment. Other parts LGTM.
Superjomn
force-pushed
the
upgrade-megatron-0-16
branch
from
440c5f3 to
029b394
Compare
hchings
reviewed
Apr 3, 2026
| "model_extra", | ||
| "executor_extra", | ||
| "model", | ||
| "model_weights", |
Collaborator
There was a problem hiding this comment.
@Superjomn Is this section for backward compatibility (for older trtllm version before we have the fine-grained labels)? If yes, then it should be exactly the same as the old tags at https://github.com/verl-project/verl/pull/5841/changes#diff-4d19b99d5dc8054a16c391ce00301671727c4c3549ecb6d904d33c2aa1f552beL263 (aka without model_weights and draft_model_weights). Otherwise I think it'll error out.
Collaborator
Author
There was a problem hiding this comment.
Sure, let me update it.
Superjomn
changed the title
Update DeepEP branch from v1.2.1 to hybrid-ep (removing the now-unnecessary patch) and add CCCL CPATH for build compatibility. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Signed-off-by: Erin Ho <14718778+hchings@users.noreply.github.com> cleanup
Signed-off-by: Erin Ho <14718778+hchings@users.noreply.github.com>
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
…d import Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
ExecutorMemoryType is not yet available in trtllm v1.3.0rc10. Use try/except fallback so sleep mode gracefully degrades on older versions. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
The TRT-LLM 1.3.0rc10 base image ships with a newer CUDA toolkit that requires a newer NVIDIA driver than the CI runners have, causing "No CUDA GPUs are available" errors. Adding the cuda-compat package and setting LD_LIBRARY_PATH enables the container to run on hosts with older drivers (>= R535). Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
…allback _WEIGHTS_TAGS The fallback else branch (for older trtllm without ExecutorMemoryType) should match the original hard-coded list, which never included these tags. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
…m Dockerfile The cuda-compat fix does not address the actual CI failure (FlashInfer check_cuda_arch() error). Remove the unneeded apt install and LD_LIBRARY_PATH override added in 029b394. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Superjomn
force-pushed
the
upgrade-megatron-0-16
branch
from
d475420 to
6e88b33
Compare
…detection Co-Authored-By: Claude <noreply@anthropic.com>
Co-Authored-By: Claude <noreply@anthropic.com>
The Volcengine runner API (vemlp-github-runner@v1) can only pull images from the Volcengine registry. Using the DockerHub image caused a jq parse failure (exit code 5) in the setup job. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
…ibility FlashInfer's check_cuda_arch() fails when SM 7.0 (Volta) is included. Set explicit arch list (7.5;8.0;8.9;9.0;10.0;12.0+PTX) on all 4 GPU jobs to match CI L20 runners (SM 8.9). Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
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
3 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.
What does this PR do?
This PR bump up the trtllm docker image to v1.3.0rc10.
Checklist Before Starting
[{modules}] {type}: {description}(This will be checked by the CI){modules}includefsdp,megatron,veomni,sglang,vllm,rollout,trainer,ci,training_utils,recipe,hardware,deployment,ray,worker,single_controller,misc,perf,model,algo,env,tool,ckpt,doc,data,cfg,reward,fully_async,one_step_off,like[megatron, fsdp, doc]{type}is infeat,fix,refactor,chore,test[BREAKING]to the beginning of the title.[BREAKING][fsdp, megatron] feat: dynamic batchingTest
API and Usage Example
# Add code snippet or script demonstrating how to use thisDesign & Code Changes
Checklist Before Submitting
Important
Please check all the following items before requesting a review, otherwise the reviewer might deprioritize this PR for review.
pre-commit install && pre-commit run --all-files --show-diff-on-failure --color=alwaysci-requestchannel in theverlSlack workspace. (If not accessible, please try the Feishu group (飞书群).)recipesubmodule, please also update the reference to the submodule commit viagit submodule update --remoteorcd recipe && git pull origin main.