diff --git a/configs/nvidia-master.yaml b/configs/nvidia-master.yaml index 9f23f9452..5d333e040 100644 --- a/configs/nvidia-master.yaml +++ b/configs/nvidia-master.yaml @@ -7787,7 +7787,7 @@ dsv4-fp4-gb300-dynamo-vllm-agentic-mtp-agg: ep: 1 dp-attn: false - spec-decoding: mtp - conc-list: [8] + conc-list: [1, 2, 4, 6, 8] prefill: num-worker: 1 tp: 4 diff --git a/perf-changelog.yaml b/perf-changelog.yaml index 70522669d..cfb0b4daa 100644 --- a/perf-changelog.yaml +++ b/perf-changelog.yaml @@ -6317,3 +6317,11 @@ pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/2647 append-only: true +- config-keys: + - dsv4-fp4-gb300-dynamo-vllm-agentic-mtp-agg + scenario-type: + - agentic-coding + description: + - "Expand the GB300 AgentX aggregate TP4 sweep to concurrency 1, 2, 4, 6, and 8." + pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/2676 +