diff --git a/benchmarks/single_node/agentic/minimaxm3_fp4_b300_trt_mtp.sh b/benchmarks/single_node/agentic/minimaxm3_fp4_b300_trt_mtp.sh index 1e7c3f529c..df11cae903 100755 --- a/benchmarks/single_node/agentic/minimaxm3_fp4_b300_trt_mtp.sh +++ b/benchmarks/single_node/agentic/minimaxm3_fp4_b300_trt_mtp.sh @@ -119,7 +119,7 @@ enable_chunked_prefill: true enable_autotuner: true trust_remote_code: true reasoning_parser: minimax_m3 -stream_interval: 100 +stream_interval: 20 print_iter_log: true num_postprocess_workers: 8 enable_attention_dp: false diff --git a/perf-changelog.yaml b/perf-changelog.yaml index 55fc4f8671..0d2371a90e 100644 --- a/perf-changelog.yaml +++ b/perf-changelog.yaml @@ -6225,3 +6225,11 @@ - "Add a TP2/EP2 HiCache branch and update the resident recipes with extra_buffer_lazy, ReplaySSM speculative verification, and checkpoint page-cache release." - "Select TP4 C1/C2/C4/C8/C12/C20/C24, TP2/EP2 resident C4/C8/C12/C20, and TP2/EP2 HiCache C22/C24/C28/C32/C40 with golden synthetic acceptance length 3.39." pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/2660 + +- config-keys: + - minimaxm3-fp4-b300-trtllm-agentic-mtp + scenario-type: + - agentic-coding + description: + - "Refresh with lower stream interval to collect correct client metrics" + pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/2685