From f34a99e17229351aacc2f9d2cbf40fac0ee59f29 Mon Sep 17 00:00:00 2001 From: ppalanga Date: Thu, 30 Apr 2026 07:03:16 -0700 Subject: [PATCH 1/3] Update amd-master.yaml --- .github/configs/amd-master.yaml | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/.github/configs/amd-master.yaml b/.github/configs/amd-master.yaml index 1faf3682b..56719dacf 100644 --- a/.github/configs/amd-master.yaml +++ b/.github/configs/amd-master.yaml @@ -1,5 +1,5 @@ dsr1-fp4-mi355x-sglang: - image: lmsysorg/sglang:v0.5.9-rocm700-mi35x + image: lmsysorg/sglang:v0.5.10.post1-rocm720-mi35x model: amd/DeepSeek-R1-0528-MXFP4-Preview model-prefix: dsr1 runner: mi355x From 77e8ca8cc1fc4a2007bb35ebf11ca32c274d67ce Mon Sep 17 00:00:00 2001 From: ppalanga Date: Thu, 30 Apr 2026 07:08:08 -0700 Subject: [PATCH 2/3] Update perf-changelog.yaml --- perf-changelog.yaml | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/perf-changelog.yaml b/perf-changelog.yaml index ae2b88f03..23fc90dc0 100644 --- a/perf-changelog.yaml +++ b/perf-changelog.yaml @@ -2031,3 +2031,9 @@ - "Topologies mirror the dsv4-fp4-gb300-dynamo-vllm sibling: low-conc 1p1d-dep8-tep8 (4 nodes), mid 1p1d-dep8-dep16 (6 nodes), high 3p1d-dep8-dep16 (10 nodes). 4096 overlap between mid and high gives a topology-crossover A/B" - "No upstream GB300 DSV4 sglang disagg recipe exists. Per-worker sglang_config (env vars + flashinfer_mxfp4 + chunked-prefill-size 4096 + disable-flashinfer-autotune + mem-fraction-static 0.82) is mirrored from NVIDIA/srt-slurm PR #69 (recipes/gb300-fp4/1k1k-dsv4/agg-2n-low-latency.yaml — GB300 DSV4 SGLang aggregated). Disagg flag set (nixl transfer backend, enable-dp-attention + moe-a2a-backend deepep) cross-checked against PR #75 (recipes/gb300-fp4/1k1k-dsv4/disagg-1p1d-tp4-mxfp4.yaml — GB300 DSV4 SGLang disagg) and the SGLang DeepSeek-V4 cookbook. Stored under benchmarks/multi_node/srt-slurm-recipes/sglang/deepseek-v4/ and overlaid onto the upstream srt-slurm checkout at runtime" pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/1157 + +- config-keys: + - dsr1-fp4-mi355x-sglang + description: + - "Updating MI355x Deepseek-R1 FP4 SGLang Image to upstream v0.5.10.post1" + pr-link: https://github.com/InferenceMAX/InferenceMAX/pull/1237 From 60bd698d739eeab4dd0acc7982501f8e52ecbd13 Mon Sep 17 00:00:00 2001 From: ppalanga Date: Thu, 30 Apr 2026 07:48:44 -0700 Subject: [PATCH 3/3] Update perf-changelog.yaml Co-authored-by: claude[bot] <209825114+claude[bot]@users.noreply.github.com> --- perf-changelog.yaml | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/perf-changelog.yaml b/perf-changelog.yaml index 23fc90dc0..1a11a9412 100644 --- a/perf-changelog.yaml +++ b/perf-changelog.yaml @@ -2036,4 +2036,4 @@ - dsr1-fp4-mi355x-sglang description: - "Updating MI355x Deepseek-R1 FP4 SGLang Image to upstream v0.5.10.post1" - pr-link: https://github.com/InferenceMAX/InferenceMAX/pull/1237 + pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/1237