From 77a7868061be7199bb7ea8fa02d5bf7eb56cbd5f Mon Sep 17 00:00:00 2001 From: "claude[bot]" <41898282+claude[bot]@users.noreply.github.com> Date: Fri, 30 Oct 2026 20:27:38 +0000 Subject: [PATCH 1/2] chore(dsv41flash): bump MI355X vLLM AgentX DSpark image to nightly-335dd77b Co-Authored-By: Claude Opus 5.5 --- inferencex-e2e/configs/amd-master.yaml | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/inferencex-e2e/configs/amd-master.yaml b/inferencex-e2e/configs/amd-master.yaml index d90bcbb422..ba659fb499 100644 --- a/inferencex-e2e/configs/amd-master.yaml +++ b/inferencex-e2e/configs/amd-master.yaml @@ -1184,7 +1184,7 @@ dsv41flash-fp4-mi355x-vllm-agentic-dspark: # ROCm 10.0 nightly carrying vllm-project/vllm#59039 (decoder SWA bounded # replay on ROCm), #61082 (mono decode on all 40 backbone layers) and #62131 # (mono decode on the DSpark draft layers), all switched by --monokernel. - image: vllm/vllm-openai-rocm:nightly-e68efc685ab1e6f1eda004ced7157e3ca411da2f@sha256:520e098f54ec96837228aaddea0a833cbf6374dbdffd480c1d65f26ffab7701b + image: vllm/vllm-openai-rocm:nightly-335dd77b09161c5d63139b4e7ae51bb9928305b1@sha256:3c634cc2c51eda7eb840a236b1f09a5ecf6a4b0cb92c4b8486e2158770507291 model: deepseek-ai/DeepSeek-V4.1-Flash model-prefix: dsv41flash runner: cluster:mi355x-amds From 0bd34344dc94277f8aa3d705e7f88cd36e4a59ef Mon Sep 17 00:00:00 2001 From: "claude[bot]" <41898282+claude[bot]@users.noreply.github.com> Date: Fri, 30 Oct 2026 21:08:19 +0000 Subject: [PATCH 2/2] perf-changelog: dsv41flash MI355X vLLM AgentX DSpark image to nightly-335dd77b Co-Authored-By: Claude Opus 5.5 --- inferencex-e2e/perf-changelog.yaml | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/inferencex-e2e/perf-changelog.yaml b/inferencex-e2e/perf-changelog.yaml index 124c53d70a..bc6accd078 100644 --- a/inferencex-e2e/perf-changelog.yaml +++ b/inferencex-e2e/perf-changelog.yaml @@ -11703,3 +11703,10 @@ - "Disagg 3 × DEP2 prefill and 1 × DEP16 decode at c1228 (override_3p1d_dep2_dep16_c1228) on nightly-dev-cu13-20261028-586355a8, with the prefill host-DRAM HiCache base recipe and the retired key's c1228 decode sizing: max-running-requests 384, decode CUDA graph batch 24, disaggregation-decode-extra-slots 36." pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/4679 append-only: true + +- config-keys: + - dsv41flash-fp4-mi355x-vllm-agentic-dspark + scenario-type: [agentic-coding] + description: + - "Update vLLM ROCm image from nightly-e68efc68 to nightly-335dd77b, pinned by digest." + pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/4685