[None][fix] Raise server_waiting_timeout to 3600s for DSv4 disagg tests#14028
Open
Shixiaowei02 wants to merge 2 commits into
Open
[None][fix] Raise server_waiting_timeout to 3600s for DSv4 disagg tests#14028Shixiaowei02 wants to merge 2 commits into
Shixiaowei02 wants to merge 2 commits into
Conversation
Shixiaowei02
force-pushed
the
user/xiaoweis/dsv4_disagg_timeout
branch
from
131fb75 to
8e4686e
Compare
Collaborator
Author
|
/bot run --add-multi-gpu-test --disable-fail-fast |
Barry-Delaney
approved these changes
May 12, 2026
Collaborator
|
PR_Github #47876 [ run ] triggered by Bot. Commit: |
Collaborator
|
PR_Github #47876 [ run ] completed with state
|
V4-Flash safetensors prefetch (~148 GB at ~90 MB/s on shared scratch) plus autotuner and CUDA graph warmup needs ~37 min/worker at TP=2, exceeding the 2100s (35 min) default. The wait loop times out, then pytest.fail short-circuits the with-block before yield, and cleanup hangs in Popen.wait() until the 60 min @pytest.mark.timeout kills it. Signed-off-by: Xiaowei Shi <39303645+Shixiaowei02@users.noreply.github.com>
…DIA#14024)" This reverts commit f2af68f. Signed-off-by: Xiaowei Shi <39303645+Shixiaowei02@users.noreply.github.com>
Shixiaowei02
force-pushed
the
user/xiaoweis/dsv4_disagg_timeout
branch
from
8e4686e to
8410783
Compare
Collaborator
Author
|
/bot run --add-multi-gpu-test --disable-fail-fast |
Collaborator
|
PR_Github #47929 [ run ] triggered by Bot. Commit: |
Collaborator
|
PR_Github #47929 [ run ] completed with state |
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
V4-Flash safetensors prefetch (~148 GB at ~90 MB/s on shared scratch) plus autotuner and CUDA graph warmup needs ~37 min/worker at TP=2, exceeding the 2100s (35 min) default. The wait loop times out, then pytest.fail short-circuits the with-block before yield, and cleanup hangs in Popen.wait() until the 60 min @pytest.mark.timeout kills it.
@coderabbitai summary
Description
Test Coverage
PR Checklist
Please review the following before submitting your PR:
PR description clearly explains what and why. If using CodeRabbit's summary, please make sure it makes sense.
PR Follows TRT-LLM CODING GUIDELINES to the best of your knowledge.
Test cases are provided for new code paths (see test instructions)
Any new dependencies have been scanned for license and vulnerabilities
CODEOWNERS updated if ownership changes
Documentation updated as needed
Update tava architecture diagram if there is a significant design change in PR.
The reviewers assigned automatically/manually are appropriate for the PR.
Please check this after reviewing the above items as appropriate for this PR.
GitHub Bot Help
To see a list of available CI bot commands, please comment
/bot help.