Non-record: AWQ 2xH100 proxy no-compile quantized eval#1976
Open
Devchandrasen wants to merge 1 commit intoopenai:mainfrom
Open
Non-record: AWQ 2xH100 proxy no-compile quantized eval#1976Devchandrasen wants to merge 1 commit intoopenai:mainfrom
Devchandrasen wants to merge 1 commit intoopenai:mainfrom
Conversation
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Non-record submission for the 16MB track.
This adds a 2xH100 proxy run based on the PR #1956 / PR #1908 AWQ + GPTQ stack. It is not intended as a leaderboard/SOTA claim because it was run on 2xH100 rather than the official 8xH100 setup.
Result:
The original run produced an under-16MB artifact. On my PyTorch 2.8.0 + CUDA 12.8 HPC setup, compiled quantized evaluation crashed after decompression, so the included train_gpt.py adds an environment-gated no-compile quantized eval path. The saved artifact was then reloaded and evaluated successfully with exit status 0.