From 188c26f4d4f49934ec8ba77e067736b24a14ecc7 Mon Sep 17 00:00:00 2001 From: functionstackx <47992694+functionstackx@users.noreply.github.com> Date: Mon, 18 May 2026 02:16:02 -0400 Subject: [PATCH 1/2] Update dsr1-fp8-h200-trt (+mtp) TRT-LLM image to v1.3.0rc14 Update TensorRT-LLM image from v1.1.0rc2.post2 (154d/124d old) to v1.3.0rc14 (latest pre-release) Co-Authored-By: Claude Opus 4.7 (1M context) --- .github/configs/nvidia-master.yaml | 4 ++-- perf-changelog.yaml | 7 +++++++ 2 files changed, 9 insertions(+), 2 deletions(-) diff --git a/.github/configs/nvidia-master.yaml b/.github/configs/nvidia-master.yaml index 34a422f1c..400866556 100644 --- a/.github/configs/nvidia-master.yaml +++ b/.github/configs/nvidia-master.yaml @@ -3141,7 +3141,7 @@ glm5-fp8-h200-sglang: - { tp: 8, conc-start: 4, conc-end: 64 } dsr1-fp8-h200-trt: - image: nvcr.io#nvidia/tensorrt-llm/release:1.1.0rc2.post2 + image: nvcr.io#nvidia/tensorrt-llm/release:1.3.0rc14 model: deepseek-ai/DeepSeek-R1-0528 model-prefix: dsr1 runner: h200 @@ -3164,7 +3164,7 @@ dsr1-fp8-h200-trt: - { tp: 8, ep: 8, dp-attn: true, conc-start: 64, conc-end: 64 } dsr1-fp8-h200-trt-mtp: - image: nvcr.io#nvidia/tensorrt-llm/release:1.1.0rc2.post2 + image: nvcr.io#nvidia/tensorrt-llm/release:1.3.0rc14 model: deepseek-ai/DeepSeek-R1-0528 model-prefix: dsr1 runner: h200 diff --git a/perf-changelog.yaml b/perf-changelog.yaml index 6c307284d..9da9c09f0 100644 --- a/perf-changelog.yaml +++ b/perf-changelog.yaml @@ -2717,3 +2717,10 @@ 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: + - dsr1-fp8-h200-trt + - dsr1-fp8-h200-trt-mtp + description: + - "Update TensorRT-LLM image from v1.1.0rc2.post2 (154d/124d old) to v1.3.0rc14 (latest pre-release)" + pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/XXX From 1551f9941f64d13f4bd42daabe40b84d146c05a3 Mon Sep 17 00:00:00 2001 From: functionstackx <47992694+functionstackx@users.noreply.github.com> Date: Mon, 18 May 2026 02:16:07 -0400 Subject: [PATCH 2/2] chore: fill pr-link for #1487 --- perf-changelog.yaml | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/perf-changelog.yaml b/perf-changelog.yaml index 9da9c09f0..c65433679 100644 --- a/perf-changelog.yaml +++ b/perf-changelog.yaml @@ -2723,4 +2723,4 @@ - dsr1-fp8-h200-trt-mtp description: - "Update TensorRT-LLM image from v1.1.0rc2.post2 (154d/124d 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/1487