[Runtime][TP2 CP2] Publish strict bitwise runtime and user modes - #344
Open
inaniloquentee wants to merge 2 commits into
Open
[Runtime][TP2 CP2] Publish strict bitwise runtime and user modes#344inaniloquentee wants to merge 2 commits into
inaniloquentee wants to merge 2 commits into
Conversation
inaniloquentee
requested review from
EthanZero2Hero,
Flink-ddd,
KJLdefeated,
bitborne and
maxiaosong1124
as code owners
August 26, 2026 17:12
|
Important Review skippedAuto reviews are disabled on base/target branches other than the default branch. Please check the settings in the CodeRabbit UI or the ⚙️ Run configurationConfiguration used: defaults Review profile: CHILL Plan: Pro Plus Run ID: You can disable this status message by setting the Use the checkbox below for a quick retry:
Comment |
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
This publishes the complete RL-Kernel side of the Qwen3-8B TP=2, CP=2 strict
train/rollout consistency work on top of the current
testbranch.linear_logpruntime routes used by the 8xH100 validation;GEMM while retaining the explicit SM90 backend;
RL_KERNEL_MODE=strict|audit|auto|offas the user-facing integrationcontract;
interface,operator,actual, andfallbackonce per module onrank 0 by default;
rl_engine.integrations.vime.linear_logp.provider, while keeping the oldprovider path compatible;
or vLLM native source is modified.
The branch was rebuilt from
origin/testbefore publication, so the earlierlocal WIP snapshot is not present in the PR history.
8xH100 evidence
Qwen3-8B, TP=2, CP=2, strict aligned R/R:
Artifact directory on the validation host:
Tests
The skipped cases require CUDA.
bash -nandgit diff --checkalso pass.