Enable Rust frontend (VLLM_USE_RUST_FRONTEND=1) (#1634)

* Enable Rust frontend (VLLM_USE_RUST_FRONTEND=1)

With Rust frontend, we don't change kernel, attention, MoE GEMM, or
KV cache. So it won't change the Througput and TPOT. But it benefits
TTFT as it helps to decrease the frontend CUP time cost from the moment
of requesting to generate the first token.

* Update per-changelog

---------

Co-authored-by: functionstackx <47992694+functionstackx@users.noreply.github.com>

Author: chunfangamd

benchmarks/single_node/fixed_seq_len/minimaxm2.5_fp4_mi355x.sh

@@ -25,6 +25,7 @@ if [ -n "$ROCR_VISIBLE_DEVICES" ]; then
 fi
 
 export VLLM_ROCM_USE_AITER=1
+export VLLM_USE_RUST_FRONTEND=1
 EXTRA_VLLM_ARGS=""
 # if [ "$TP" -ge 4 ]; then
 #     # AITER CK fused MoE kernels lack compiled tiles for N=intermediate_size/TP

perf-changelog.yaml

@@ -3523,3 +3523,11 @@
     - "Aligned decode params with Weiliang config: swa-full-tokens-ratio=0.20, max-running-requests=18432, moe-dense-tp-size=1; added prefill enable-dp-lm-head and cuda-graph-max-bs=512"
     - "Remove 4 dominated old configs (4p-dep16-8n, 8p-dep16-12n, 10p-dep16-14n, 12p-dep12-15n) superseded by wide-EP frontier"
   pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/1586
+
+- config-keys:
+    - minimaxm2.5-fp4-mi355x-vllm
+  description:
+    - "Enable vLLM Rust request frontend by exporting VLLM_USE_RUST_FRONTEND=1 in benchmarks/single_node/minimaxm2.5_fp4_mi355x.sh (v0.22.0 ROCm image ships the vllm-rs binary, so the flag engages it). Environment-only change; serve flags, TP/EP, attention/kernel settings unchanged"
+    - "The Rust frontend replaces only the Python serving/API layer (HTTP, tokenization, scheduling glue, detokenization) and spawns the same Python EngineCore, so GPU kernels/attention/MoE GEMM/KV cache are untouched"
+    - "A/B sweep (28 single-node points, 1k1k + 8k1k, TP 1/2/4) vs the Python-frontend baseline (run 26696260751): throughput Pareto-neutral (peak tok/s/GPU within <1.5%, frontiers coincident) and TPOT flat (+-0.5%); TTFT improves ~8% at 1k1k and ~22% at 8k1k (every point), the expected signature of lower frontend CPU latency before first token, scaling with input length"
+  pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/1634