Skip to content

Commit bfac96d

Browse files
author
claude-rebase-bot
committed
Merge remote-tracking branch 'origin/main' into HEAD
# Conflicts: # perf-changelog.yaml
2 parents 6ff1a34 + 5a2a254 commit bfac96d

2 files changed

Lines changed: 7 additions & 1 deletion

File tree

.github/configs/nvidia-master.yaml

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -4655,7 +4655,7 @@ dsr1-fp8-h100-dynamo-sglang:
46554655
dp-attn: true
46564656

46574657
gptoss-fp4-h200-trt:
4658-
image: nvcr.io#nvidia/tensorrt-llm/release:1.3.0rc11
4658+
image: nvcr.io#nvidia/tensorrt-llm/release:1.3.0rc14
46594659
model: openai/gpt-oss-120b
46604660
model-prefix: gptoss
46614661
runner: h200

perf-changelog.yaml

Lines changed: 6 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -2815,6 +2815,12 @@
28152815
- "Update vLLM image from v0.19.0-cu130 (26d old) to v0.21.0"
28162816
pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/1453
28172817

2818+
- config-keys:
2819+
- gptoss-fp4-h200-trt
2820+
description:
2821+
- "Update TensorRT-LLM image from v1.3.0rc11 (34d old) to v1.3.0rc14 (latest pre-release)"
2822+
pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/1491
2823+
28182824
- config-keys:
28192825
- qwen3.5-fp4-b300-sglang
28202826
- qwen3.5-fp4-b300-sglang-mtp

0 commit comments

Comments
 (0)