[Klaud Cold] Update dsv4-fp8-h200-vllm (+mtp) vLLM image to v0.22.0

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

Author: functionstackx

.github/configs/nvidia-master.yaml

@@ -2884,7 +2884,7 @@ dsr1-fp8-h200-sglang-mtp:
 # Uses the cu129 image. H200 has no FP4 path, so the FP4 indexer cache
 # flag is omitted. Max-model-len is pinned at 800k per the recipe.
 dsv4-fp8-h200-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: h200
@@ -2908,7 +2908,7 @@ dsv4-fp8-h200-vllm:
 # (the non-MTP entry above is still on the deepseekv4-cu129 tag) and adds
 # --speculative-config '{"method":"mtp","num_speculative_tokens":2}'.
 dsv4-fp8-h200-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: h200

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-fp8-h200-vllm
+    - dsv4-fp8-h200-vllm-mtp
+  description:
+    - "Update vLLM image from v0.21.0 to v0.22.0"
+  pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/1597