diff --git a/inferencex-e2e/benchmarks/multi_node/srt-slurm-recipes/kimik3.1/vllm/gb200-fp4/agentx/agg-tp8pp2-variants.yaml b/inferencex-e2e/benchmarks/multi_node/srt-slurm-recipes/kimik3.1/vllm/gb200-fp4/agentx/agg-tp8pp2-variants.yaml index ef97d6303d..bf2f986c83 100644 --- a/inferencex-e2e/benchmarks/multi_node/srt-slurm-recipes/kimik3.1/vllm/gb200-fp4/agentx/agg-tp8pp2-variants.yaml +++ b/inferencex-e2e/benchmarks/multi_node/srt-slurm-recipes/kimik3.1/vllm/gb200-fp4/agentx/agg-tp8pp2-variants.yaml @@ -36,6 +36,8 @@ base: env: VLLM_ENGINE_READY_TIMEOUT_S: "3600" VLLM_RPC_TIMEOUT: "600000" + # AIPerf reuses a session's connection across turns; outlast uvicorn's 5 s idle timeout. + VLLM_HTTP_TIMEOUT_KEEP_ALIVE: "600" NCCL_CUMEM_ENABLE: "1" NCCL_MNNVL_ENABLE: "1" NCCL_NVLS_ENABLE: "1" diff --git a/inferencex-e2e/perf-changelog.yaml b/inferencex-e2e/perf-changelog.yaml index 49c3625b4f..d1912fb1f3 100644 --- a/inferencex-e2e/perf-changelog.yaml +++ b/inferencex-e2e/perf-changelog.yaml @@ -12471,3 +12471,13 @@ description: - "The H3 client polls job status every 0.1 s instead of every 0.5 s. A job counts as done only at the next poll, so each published latency carried up to 0.5 s of polling delay; it now carries up to 0.1 s." pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/4904 + +- config-keys: + - kimik3.1-fp4-gb200-vllm-agentic-dspark-tp8pp2-agg + - kimik3.1-fp4-gb200-vllm-agentic-dspark-tp16-disagg + scenario-type: + - agentic-coding + description: + - "Re-sweep Kimi-K3.1-Pro GB200 vLLM AgentX with the updated DSpark draft (Inferact/Kimi-K3.1-Pro-DSpark-preview @ 6a2ef20a) and the #4851 golden curve, so throughput forces AL 3.41 at 5 draft tokens and 3.19 at 4." + - "Set VLLM_HTTP_TIMEOUT_KEEP_ALIVE to 600 s on the aggregated server so AIPerf's reused session connections outlive uvicorn's 5 s idle timeout." + pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/4864