From c58c4acc81cba76d83256dceaa329b7d60b0bee7 Mon Sep 17 00:00:00 2001 From: functionstackx <47992694+functionstackx@users.noreply.github.com> Date: Mon, 18 May 2026 02:16:34 -0400 Subject: [PATCH 1/2] Update gptoss-fp4-b200-trt TRT-LLM image to v1.3.0rc14 Update TensorRT-LLM image from v1.2.0rc2.post2 (102d old) to v1.3.0rc14 (latest pre-release) Co-Authored-By: Claude Opus 4.7 (1M context) --- .github/configs/nvidia-master.yaml | 2 +- perf-changelog.yaml | 6 ++++++ 2 files changed, 7 insertions(+), 1 deletion(-) diff --git a/.github/configs/nvidia-master.yaml b/.github/configs/nvidia-master.yaml index 34a422f1c..7c701d7e2 100644 --- a/.github/configs/nvidia-master.yaml +++ b/.github/configs/nvidia-master.yaml @@ -4177,7 +4177,7 @@ dsr1-fp8-h100-dynamo-trt: dp-attn: true gptoss-fp4-b200-trt: - image: nvcr.io#nvidia/tensorrt-llm/release:1.2.0rc2.post2 + image: nvcr.io#nvidia/tensorrt-llm/release:1.3.0rc14 model: openai/gpt-oss-120b model-prefix: gptoss runner: b200 diff --git a/perf-changelog.yaml b/perf-changelog.yaml index 6c307284d..ff87a1966 100644 --- a/perf-changelog.yaml +++ b/perf-changelog.yaml @@ -2717,3 +2717,9 @@ description: - "Update SGLang image from v0.5.10-rocm720-mi30x to v0.5.12-rocm720-mi30x" pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/1426 + +- config-keys: + - gptoss-fp4-b200-trt + description: + - "Update TensorRT-LLM image from v1.2.0rc2.post2 (102d old) to v1.3.0rc14 (latest pre-release)" + pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/XXX From 2baba8e27be8529b4453afc953f9859ec092c73d Mon Sep 17 00:00:00 2001 From: functionstackx <47992694+functionstackx@users.noreply.github.com> Date: Mon, 18 May 2026 02:16:39 -0400 Subject: [PATCH 2/2] chore: fill pr-link for #1490 --- perf-changelog.yaml | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/perf-changelog.yaml b/perf-changelog.yaml index ff87a1966..497942c4a 100644 --- a/perf-changelog.yaml +++ b/perf-changelog.yaml @@ -2722,4 +2722,4 @@ - gptoss-fp4-b200-trt description: - "Update TensorRT-LLM image from v1.2.0rc2.post2 (102d old) to v1.3.0rc14 (latest pre-release)" - pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/XXX + pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/1490