From 1f78380be87403e9239a44421a22b206f06c93f7 Mon Sep 17 00:00:00 2001 From: Cam Quilici Date: Tue, 14 Jul 2026 00:02:58 -0500 Subject: [PATCH] fix(agentic): remove warmup drain timeout --- benchmarks/benchmark_lib.sh | 3 +++ 1 file changed, 3 insertions(+) diff --git a/benchmarks/benchmark_lib.sh b/benchmarks/benchmark_lib.sh index 0085493aa..2fc68c013 100644 --- a/benchmarks/benchmark_lib.sh +++ b/benchmarks/benchmark_lib.sh @@ -1479,6 +1479,9 @@ build_replay_cmd() { # with one-token outputs and no idle delays for 10 minutes. Profiling begins # only after those requests drain and resumes from the resulting live state. REPLAY_CMD+=" --agentic-cache-warmup-duration 600" + # Long-context warmup requests can take more than AIPerf's default 300s + # grace period to drain. Wait for every warmup request before profiling. + REPLAY_CMD+=" --warmup-grace-period inf" # Use server-reported usage fields (prompt_tokens / completion_tokens) for # ISL/OSL instead of client-side tokenizer.encode(). Auto-enables # stream_options.include_usage on the OpenAI chat endpoint. Skips the