Add Kimi-K2-Thinking NVFP4/INT4 gsm8k accuracy coverage (4xB200)#40
Open
stecasta wants to merge 1 commit into
Open
Add Kimi-K2-Thinking NVFP4/INT4 gsm8k accuracy coverage (4xB200)#40stecasta wants to merge 1 commit into
stecasta wants to merge 1 commit into
Conversation
Adds 4xB200 (TP=4 + EP) accuracy-only recipes (lm_eval gsm8k) for Kimi-K2-Thinking NVFP4 and INT4, extending Blackwell large-MoE coverage so quantized correctness regressions surface in nightly instead of downstream. Signed-off-by: Stefano Castagnetta <scastagnetta@nvidia.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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Adds Kimi-K2-Thinking accuracy recipes on 4xB200 (TP=4 + EP) to the nightly, extending Blackwell large-MoE coverage so quantized correctness regressions surface in nightly instead of downstream.
Reference gsm8k (vLLM CI gsm8k harness, 5-shot / 1319q):
Accuracy-only (lm_eval gsm8k, completions path). Validated locally (parse_workload + generate_pipeline); B200 nightly run to follow.
AI-assisted (Claude Code).