diff --git a/configs/amd-master.yaml b/configs/amd-master.yaml index 7fa80d605..85745ccdc 100644 --- a/configs/amd-master.yaml +++ b/configs/amd-master.yaml @@ -1316,7 +1316,7 @@ qwen3.5-fp8-mi325x-sglang-mtp: - { tp: 8, ep: 1, conc-start: 4, conc-end: 64, spec-decoding: mtp } dsv4-fp4-mi355x-vllm-agentic-mtp: - image: vllm/vllm-openai-rocm:nightly-311b3513af33bc29b4acb2fde2e9313e5e9966a0 + image: vllm/vllm-openai-rocm:nightly-e962733e08d10f7ca65dac4df99e116460b8b174 model: deepseek-ai/DeepSeek-V4-Pro model-prefix: dsv4 runner: cluster:mi355x-amds diff --git a/perf-changelog.yaml b/perf-changelog.yaml index 912728b2e..58f5e400f 100644 --- a/perf-changelog.yaml +++ b/perf-changelog.yaml @@ -6902,3 +6902,11 @@ - "Lower mem-fraction-static from 0.89 to 0.86 on every arm: TP4, TP8 and TP8 with DP attention. swa-full-tokens-ratio becomes per-arm: 0.10 on the tensor-parallel arms as before, 0.15 under DP attention." - "Drop concurrency 2 and 10 from the TP4 arm, leaving [1, 4, 8], and drop concurrency 16 from the TP8 hicache arm, leaving [32, 48]. Concurrency 16 remains on the TP8 no-offload arm." pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/2800 + +- config-keys: + - dsv4-fp4-mi355x-vllm-agentic-mtp + scenario-type: + - agentic-coding + description: + - "Repin the image from vllm/vllm-openai-rocm:nightly-311b3513af33bc29b4acb2fde2e9313e5e9966a0 to the 2026-09-05 ROCm nightly (nightly-e962733e08d10f7ca65dac4df99e116460b8b174, digest sha256:511755968434e26da590c3398f1e8a6399be4416226d5779ce92fb0655811a9c). Docker Hub last pushed it at 2026-09-05T05:27:09Z and the tag commit is vllm-project/vllm@e962733e." + pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/2841