[bugfix]: drop dead h3_sequential_load from Spark FastH3 presets - #37
Closed
aryan5v wants to merge 29 commits into
Closed
[bugfix]: drop dead h3_sequential_load from Spark FastH3 presets#37aryan5v wants to merge 29 commits into
aryan5v wants to merge 29 commits into
Conversation
Co-authored-by: Aryan Kumar <aryan5v@users.noreply.github.com>
Co-authored-by: Aryan Kumar <aryan5v@users.noreply.github.com> Co-authored-by: coderabbitai[bot] <136622811+coderabbitai[bot]@users.noreply.github.com>
…nse GEMM (hao-ai-lab#1788) Co-authored-by: Aryan Kumar <aryan5v@users.noreply.github.com>
Co-authored-by: Aryan Kumar <aryan5v@users.noreply.github.com>
Co-authored-by: Aryan Kumar <aryan5v@users.noreply.github.com>
…ab#1793) Co-authored-by: Aryan Kumar <aryan5v@users.noreply.github.com>
Co-authored-by: Aryan Kumar <aryan5v@users.noreply.github.com>
Co-authored-by: Aryan Kumar <aryan5v@users.noreply.github.com>
Co-authored-by: Shahrad Zomorrodi <264690209+shahradzomorrodi@users.noreply.github.com>
…ao-ai-lab#1803) Co-authored-by: Kyle <shh075@ucsd.edu> Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com> Co-authored-by: Satyam Srivastava <srivastavasatyam53@gmail.com> Co-authored-by: Aryan Kumar <aryan5v@users.noreply.github.com>
hao-ai-lab#1805) Co-authored-by: Vaish, Ishan <isvaish@UCSD.EDU> Co-authored-by: Claude Sonnet 5 <noreply@anthropic.com>
…hao-ai-lab#1811) Co-authored-by: Aryan Kumar <aryan5v@users.noreply.github.com>
Signed-off-by: lishunyang12 <lishunyang12@163.com>
lazy_module_load owns deferral on GB10 and suppresses h3_sequential_load. Remove the inert flag from the three Spark YAML presets and add a regression test. Co-authored-by: Aryan Kumar <aryan5v@users.noreply.github.com>
|
Too many files changed for review (324 files, 100 file limit). Bypass the limit by tagging |
|
Important Review skippedToo many files! This PR contains 322 files, which is 222 over the limit of 100. To get a review, reduce the PR to 100 files or fewer by splitting it into smaller PRs or changing its base branch. Upgrade to a paid plan to raise the limit. Usage-priced reviews support at most 300 files. ⚙️ Run configurationConfiguration used: defaults Review profile: CHILL Plan: Advanced Run ID: ⛔ Files ignored due to path filters (2)
📒 Files selected for processing (322)
You can disable this status message by setting the Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. 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
11 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.
Why
The three Spark FastH3 YAML presets set both
lazy_module_load: trueandh3_sequential_load: true. On GB10,lazy_module_loadowns component deferral andMiniMaxH3Pipeline._defer_denoise_modulesturns sequential load off when lazy is on (hao-ai-lab#1803 review). Theh3_sequential_loadlines were inert and implied two deferral paths were active.Scope
h3_sequential_load: truefrom:examples/inference/basic/basic_fasth3_spark.yamlexamples/inference/basic/basic_fasth3_spark_pair.yamlexamples/serving/openai_fasth3_spark.yamltest_spark_configs_use_lazy_load_not_sequentialintests/local_tests/test_cookbook_serving.pyh3_sequential_loadstays in the codebase as the H3 fallback when lazy is off. This change only fixes the Spark presets.Tradeoffs
None. The removed flag had no runtime effect while
lazy_module_loadwas true.Blast radius
Example configs and one local test. No loader or pipeline code changes.
Verification
test_spark_configs_use_lazy_load_not_sequentialassertslazy_module_load is Trueandh3_sequential_loadis absent frompipeline.experimentalfor all three presets./no-comments(Comment Sicko): dropped redundant YAML comments; kept the regression test without inline narration.