From 33bcb8b282fdb3213181e9204af3ad812044675f Mon Sep 17 00:00:00 2001 From: Cam Quilici Date: Thu, 5 Nov 2026 14:28:16 -0600 Subject: [PATCH 1/2] chore(changelog): re-run Kimi-K3.1-Pro vLLM B300 with synthetic parsers off [skip-sweep] --- inferencex-e2e/perf-changelog.yaml | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/inferencex-e2e/perf-changelog.yaml b/inferencex-e2e/perf-changelog.yaml index bc808e6451..4c021e3a64 100644 --- a/inferencex-e2e/perf-changelog.yaml +++ b/inferencex-e2e/perf-changelog.yaml @@ -12099,3 +12099,11 @@ - "Disaggregated: TP8/DCP8 prefill with a HiCache host tier feeding either one TP16 (DCP8 x attention DP2, EP16 MegaMoE) decode worker (3P1D c300, 2P1D c180, 1P1D c76) or TP8/DCP8 decode workers (1P3D c60 and c36, 1P4D c32)." - "Aggregated low-latency points: one TP16 EP1 worker with the NVIDIA megakernel (--enable-nvidia-megakernel), max-running-requests equal to the concurrency (c1, c2, c4)." pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/4811 + +- config-keys: + - kimik3.1-fp4-b300-vllm-agentic-dspark + scenario-type: + - agentic-coding + description: + - "Re-run Kimi-K3.1-Pro vLLM AgentX on B300 with the tool and reasoning parsers off on synthetic-acceptance throughput servers (#4840); evals keep them." + pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/4796 From dc14efe3d41fdff6a7e91cb53074058b802bc679 Mon Sep 17 00:00:00 2001 From: Cam Quilici Date: Thu, 5 Nov 2026 14:28:32 -0600 Subject: [PATCH 2/2] chore(changelog): link the B300 re-run entry to #4841 --- inferencex-e2e/perf-changelog.yaml | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/inferencex-e2e/perf-changelog.yaml b/inferencex-e2e/perf-changelog.yaml index 4c021e3a64..878e043ea8 100644 --- a/inferencex-e2e/perf-changelog.yaml +++ b/inferencex-e2e/perf-changelog.yaml @@ -12106,4 +12106,4 @@ - agentic-coding description: - "Re-run Kimi-K3.1-Pro vLLM AgentX on B300 with the tool and reasoning parsers off on synthetic-acceptance throughput servers (#4840); evals keep them." - pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/4796 + pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/4841