diff --git a/configs/amd-master.yaml b/configs/amd-master.yaml index 59f655945..40836fe2c 100644 --- a/configs/amd-master.yaml +++ b/configs/amd-master.yaml @@ -372,7 +372,7 @@ qwen3.5-fp4-mi355x-sglang-agentic-mtp: agentic-coding: - dram-utilization: 0.80 search-space: - - { tp: 2, ep: 2, spec-decoding: mtp, kv-offloading: none, conc-list: [1, 4, 8, 12, 16, 20] } + - { tp: 2, ep: 1, spec-decoding: mtp, kv-offloading: none, conc-list: [1, 4, 8, 12, 16, 20, 24, 28, 32] } - { tp: 4, ep: 1, spec-decoding: mtp, kv-offloading: none, conc-list: [1, 4, 8, 12, 16, 20, 24, 28, 32, 40] } qwen3.5-fp4-mi355x-sglang-disagg: diff --git a/perf-changelog.yaml b/perf-changelog.yaml index 93b6a7c1b..d98491b1c 100644 --- a/perf-changelog.yaml +++ b/perf-changelog.yaml @@ -6251,3 +6251,12 @@ description: - "Refresh with lower stream interval to collect correct client metrics" pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/2686 + +- config-keys: + - qwen3.5-fp4-mi355x-sglang-agentic-mtp + scenario-type: + - agentic-coding + description: + - "Replace the TP2/EP2 arm with TP2/EP1 so the 2-GPU point matches qwen3.5-fp4-b200-sglang-agentic-mtp." + - "Extend the TP2 concurrency list to 1, 4, 8, 12, 16, 20, 24, 28, and 32." + pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/2694