Skip to content

[NVIDIA] B200 TRT Update GPT-OSS configs#110

Merged
functionstackx merged 9 commits intomainfrom
kepotdar-gptoss-trt-update-jgangani
Oct 20, 2025
Merged

[NVIDIA] B200 TRT Update GPT-OSS configs#110
functionstackx merged 9 commits intomainfrom
kepotdar-gptoss-trt-update-jgangani

Conversation

@jgangani
Copy link
Copy Markdown
Collaborator

@jgangani jgangani commented Oct 16, 2025

Updates B200 TRTLLM GPTOSS configs to boost performance. Update KV$ from BF16 --> FP8

@jgangani jgangani requested a review from a team as a code owner October 16, 2025 19:59
@jgangani jgangani force-pushed the kepotdar-gptoss-trt-update-jgangani branch from 44b7e61 to cdec13f Compare October 16, 2025 20:20
@kedarpotdar-nv kedarpotdar-nv changed the title Kepotdar gptoss trt update jgangani B200 TRT Update GPT-OSS configs Oct 20, 2025
@functionstackx
Copy link
Copy Markdown
Contributor

@kedarpotdar-nv @jgangani is their an link to an validation run for at least 1 concurrency?

@kedarpotdar-nv
Copy link
Copy Markdown
Collaborator

@kedarpotdar-nv
Copy link
Copy Markdown
Collaborator

Comment thread benchmarks/gptoss_fp4_b200_trt_slurm.sh
@functionstackx functionstackx merged commit ac1998a into main Oct 20, 2025
@functionstackx functionstackx deleted the kepotdar-gptoss-trt-update-jgangani branch October 20, 2025 23:08
@cquil11 cquil11 added the NVIDIA label Apr 8, 2026
@cquil11 cquil11 changed the title B200 TRT Update GPT-OSS configs [NVIDIA] B200 TRT Update GPT-OSS configs Apr 8, 2026
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

Projects

None yet

Development

Successfully merging this pull request may close these issues.

4 participants