Add vLLM DSv4 FP8 MI355X benchmark (vllm#40889)

.github/configs/amd-master.yaml

@@ -1490,6 +1490,30 @@ dsv4-fp8-mi355x-sglang:
     search-space:
     - { tp: 8, conc-start: 4, conc-end: 64 }
 
+# vLLM with AITER MLA decode for DSv4 on MI355X (vllm-project/vllm#40889,
+# stacked on #40871). Uses the ATOM MI355X image (ROCm 7.2.2, aiter with
+# MLA decode, MI355X GPU detection); vLLM is rebuilt from the PR branch
+# at runtime by benchmarks/single_node/dsv4_fp8_mi355x_vllm.sh at a
+# pinned SHA. Once both PRs merge into a release, switch to a vLLM ROCm
+# MI355X image and remove the build step.
+dsv4-fp8-mi355x-vllm:
+  image: rocm/atom:rocm7.2.2_ubuntu24.04_py3.12_pytorch_release_2.10.0_atom0.1.2.post
+  model: deepseek-ai/DeepSeek-V4-Pro
+  model-prefix: dsv4
+  runner: mi355x
+  precision: fp8
+  framework: vllm
+  multinode: false
+  seq-len-configs:
+  - isl: 1024
+    osl: 1024
+    search-space:
+    - { tp: 8, conc-start: 1, conc-end: 32 }
+  - isl: 8192
+    osl: 1024
+    search-space:
+    - { tp: 8, conc-start: 1, conc-end: 32 }
+
 # Day-0 single-sequence marker for DeepSeek-V4 on ATOM (ROCm/ATOM#650).
 # PR1 of the ATOM DSv4 series — single-sequence only (kv_cache[:1,...]
 # hardcode), --enforce-eager required, ATOM_USE_TRITON_MOE=1 required on