diff --git a/.github/configs/nvidia-master.yaml b/.github/configs/nvidia-master.yaml index 823bbff36..637c3a9ac 100644 --- a/.github/configs/nvidia-master.yaml +++ b/.github/configs/nvidia-master.yaml @@ -3003,7 +3003,7 @@ dsv4-fp8-h200-sglang-mtp: # field, so dp-attn=true is used as the existing vLLM script switch for DP4 # layouts on 4 allocated GPUs. dsv4-fp4-b300-vllm: - image: vllm/vllm-openai:v0.21.0 + image: vllm/vllm-openai:v0.22.0 model: deepseek-ai/DeepSeek-V4-Pro model-prefix: dsv4 runner: b300 @@ -3099,7 +3099,7 @@ dsv4-fp4-b300-trt-mtp: - { tp: 8, ep: 8, dp-attn: true, conc-start: 256, conc-end: 1024, spec-decoding: mtp } dsv4-fp4-b300-vllm-mtp: - image: vllm/vllm-openai:v0.21.0 + image: vllm/vllm-openai:v0.22.0 model: deepseek-ai/DeepSeek-V4-Pro model-prefix: dsv4 runner: b300 diff --git a/perf-changelog.yaml b/perf-changelog.yaml index ad93a24b4..2af9eb286 100644 --- a/perf-changelog.yaml +++ b/perf-changelog.yaml @@ -3239,3 +3239,10 @@ - "Add --compilation-config '{\"mode\":3,\"cudagraph_mode\":\"PIECEWISE\"}' to vllm serve, mirroring `model.base_args` from the upstream recipe. `pass_config.fuse_minimax_qk_norm` from the recipe is intentionally omitted — it triggers an upstream NameError on ROCm because vllm/compilation/passes/pass_manager.py imports MiniMaxQKNormPass under `is_cuda()` (NVIDIA-only) while using it unconditionally" - "Conditionally enable VLLM_ROCM_SHUFFLE_KV_CACHE_LAYOUT=1 per (TP, EP, CONC) — on for shapes where the AITER ASM paged-attention kernel exists in the gfx942 heuristic table (TP=2 EP=1 CONC<=16, TP=8 EP=8 CONC<=64), off otherwise. Above the thresholds vllm/v1/attention/backends/rocm_aiter_fa.py routes decode through aiter pa_fwd_asm and crashes with `RuntimeError: get_heuristic_kernel: cannot get heuristic kernel!` for MiniMax-M2.5's attention shape (gqa=6 block_size=32 qTile=0); below them the ASM auto-dispatch is the perf win the recipe wants. Thresholds confirmed across 17 bench cells + 3 eval cells in PR #1594 sweep run 26692603804. Mirrors the per-shape toggle pattern in benchmarks/single_node/minimaxm2.5_fp8_mi355x.sh; can collapse to unconditional SHUFFLE=1 once AITER registers the missing kernel on gfx942" pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/1594 + +- config-keys: + - dsv4-fp4-b300-vllm + - dsv4-fp4-b300-vllm-mtp + description: + - "Update vLLM image from v0.21.0 to v0.22.0" + pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/1595