From 779ac35ca3e874bb2f973aa7f2524912a8b21328 Mon Sep 17 00:00:00 2001 From: ankursingh-nv Date: Sun, 22 Mar 2026 21:08:22 -0700 Subject: [PATCH 1/3] update sglang to v0.5.9 --- .github/configs/nvidia-master.yaml | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/.github/configs/nvidia-master.yaml b/.github/configs/nvidia-master.yaml index 4ada68395..5a6ffaf42 100644 --- a/.github/configs/nvidia-master.yaml +++ b/.github/configs/nvidia-master.yaml @@ -1650,7 +1650,7 @@ dsr1-fp8-b300-dynamo-trt: dp-attn: true dsr1-fp4-b200-sglang: - image: lmsysorg/sglang:v0.5.6-cu129-amd64 + image: lmsysorg/sglang:v0.5.9-cu130 model: nvidia/DeepSeek-R1-0528-FP4-V2 model-prefix: dsr1 runner: b200 @@ -1760,7 +1760,7 @@ dsr1-fp4-b200-trt-mtp: - { tp: 8, ep: 8, dp-attn: true, conc-start: 64, conc-end: 256, spec-decoding: mtp } dsr1-fp8-b200-sglang: - image: lmsysorg/sglang:v0.5.6-cu129-amd64 + image: lmsysorg/sglang:v0.5.9-cu130 model: deepseek-ai/DeepSeek-R1-0528 model-prefix: dsr1 runner: b200 @@ -1942,7 +1942,7 @@ kimik2.5-fp4-b200-vllm: - { tp: 4, ep: 4, conc-start: 4, conc-end: 64 } dsr1-fp8-b200-sglang-mtp: - image: lmsysorg/sglang:v0.5.8-cu130-amd64 + image: lmsysorg/sglang:v0.5.9-cu130 model: deepseek-ai/DeepSeek-R1-0528 model-prefix: dsr1 runner: b200 @@ -2021,7 +2021,7 @@ dsr1-fp8-b200-trt-mtp: - { tp: 8, ep: 1, conc-start: 4, conc-end: 256, spec-decoding: mtp } dsr1-fp8-h200-sglang: - image: lmsysorg/sglang:v0.5.9-cu129-amd64 + image: lmsysorg/sglang:v0.5.9-cu130 model: deepseek-ai/DeepSeek-R1-0528 model-prefix: dsr1 runner: h200 From ab04566edf15d6b70707a009bba551370e484006 Mon Sep 17 00:00:00 2001 From: ankursingh-nv Date: Tue, 24 Mar 2026 21:09:02 -0700 Subject: [PATCH 2/3] Add perf-changelog entry for SGLang v0.5.9-cu130 image update Co-Authored-By: Claude Opus 4.6 (1M context) --- perf-changelog.yaml | 13 +++++++++++++ 1 file changed, 13 insertions(+) diff --git a/perf-changelog.yaml b/perf-changelog.yaml index 1a19fd6a5..836a346f9 100644 --- a/perf-changelog.yaml +++ b/perf-changelog.yaml @@ -1055,3 +1055,16 @@ - "Enable VLLM_USE_FLASHINFER_MOE_INT4=1 for Kimi K2.5 INT4 B200 benchmark" pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/935 +- config-keys: + - dsr1-fp4-b200-sglang + - dsr1-fp8-b200-sglang + - dsr1-fp8-b200-sglang-mtp + - dsr1-fp8-h200-sglang + description: + - "Update SGLang image to v0.5.9-cu130 for all DSR1 SGLang configs" + - "dsr1-fp4-b200-sglang: v0.5.6-cu129-amd64 → v0.5.9-cu130" + - "dsr1-fp8-b200-sglang: v0.5.6-cu129-amd64 → v0.5.9-cu130" + - "dsr1-fp8-b200-sglang-mtp: v0.5.8-cu130-amd64 → v0.5.9-cu130" + - "dsr1-fp8-h200-sglang: v0.5.9-cu129-amd64 → v0.5.9-cu130" + pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/xxx + From db430d46a7f18b75dfbc9df1bdc828d4dee1ea9e Mon Sep 17 00:00:00 2001 From: "claude[bot]" <41898282+claude[bot]@users.noreply.github.com> Date: Wed, 25 Mar 2026 04:12:47 +0000 Subject: [PATCH 3/3] Fix perf-changelog pr-link to reference PR #943 Co-authored-by: Ankur Singh --- perf-changelog.yaml | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/perf-changelog.yaml b/perf-changelog.yaml index 836a346f9..03fb6e082 100644 --- a/perf-changelog.yaml +++ b/perf-changelog.yaml @@ -1066,5 +1066,5 @@ - "dsr1-fp8-b200-sglang: v0.5.6-cu129-amd64 → v0.5.9-cu130" - "dsr1-fp8-b200-sglang-mtp: v0.5.8-cu130-amd64 → v0.5.9-cu130" - "dsr1-fp8-h200-sglang: v0.5.9-cu129-amd64 → v0.5.9-cu130" - pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/xxx + pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/943