From 10567da5238db57c29a45e09ebd40343a7d1a543 Mon Sep 17 00:00:00 2001 From: Gahow Wang Date: Sun, 19 Jul 2026 17:11:26 +0800 Subject: [PATCH] Freeze Qwen235 ablation operator profiles --- .../qwen235-tp8-collective-profile-ablation-20260719.md | 1 + .../run_qwen235_collective_profile_ablation.sh | 2 +- 2 files changed, 2 insertions(+), 1 deletion(-) diff --git a/.research/experiments/qwen235-tp8-collective-profile-ablation-20260719.md b/.research/experiments/qwen235-tp8-collective-profile-ablation-20260719.md index 4b9365f..e4b335b 100644 --- a/.research/experiments/qwen235-tp8-collective-profile-ablation-20260719.md +++ b/.research/experiments/qwen235-tp8-collective-profile-ablation-20260719.md @@ -54,6 +54,7 @@ - **Environment：** dash0 8×H20；`/tmp/wjh/venvs/vllm-0.20.0-cu129-profiler-v1`；model `/home/admin/cpfs/wjh/models/Qwen/Qwen3-235B-A22B-FP8`。 - **产物路径：** 待 review 后冻结；不得覆盖旧 campaign `/home/admin/cpfs/wjh/aituner/qwen235-v020-fourcase-20260719-r1`。 - **已知 deviation：** `--disable-custom-all-reduce` 只关闭 vLLM custom AR，不关闭编译器的 FlashInfer `allreduce_rms` fusion。真机 TP4/TP8 日志都显示自动选择 `trtllm` workspace；旧 TP4 profiler 没有记录/执行真实 fusion-limit piecewise dispatch。A1 因此必须同时重测 TP4 与 TP8，不能只追加 TP8 行。 +- **执行异常：** 首次 simulator launch 误把 frozen operator profile root 写成 r1；原 A0 campaign 实际使用 r2。四个 Fixed-PD cells 因缺少 `attn_decode_in_mixed` predictor 均 fail-fast，未产生可用 metric。command diff 确认后停止后续运行，恢复 r2 并从 failed cells 重新执行；这些失败不计入 A1 surface。 ## 结果 diff --git a/runs/frontier-fidelity-envelope-v1/run_qwen235_collective_profile_ablation.sh b/runs/frontier-fidelity-envelope-v1/run_qwen235_collective_profile_ablation.sh index f38c5c7..1729346 100644 --- a/runs/frontier-fidelity-envelope-v1/run_qwen235_collective_profile_ablation.sh +++ b/runs/frontier-fidelity-envelope-v1/run_qwen235_collective_profile_ablation.sh @@ -6,7 +6,7 @@ BASE_CAMPAIGN_ROOT="${BASE_CAMPAIGN_ROOT:?BASE_CAMPAIGN_ROOT is required}" OUTPUT_ROOT="${OUTPUT_ROOT:?OUTPUT_ROOT is required}" ALLREDUCE_CSV="${ALLREDUCE_CSV:?ALLREDUCE_CSV is required}" RUNNER_DIR="${RUNNER_DIR:-$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)}" -PROFILE_ROOT="${PROFILE_ROOT:-/home/admin/cpfs/wjh/aituner/qwen235-v020-profiles-20260719-r1/frozen}" +PROFILE_ROOT="${PROFILE_ROOT:-/home/admin/cpfs/wjh/aituner/qwen235-v020-profiles-20260719-r2/frozen}" FRONTIER_SOURCE="${FRONTIER_SOURCE:-/home/admin/cpfs/wjh/aituner/frontier-q235-v020-5b953f5}" REPLAYSERVE_ROOT="${REPLAYSERVE_ROOT:-/home/admin/cpfs/wjh/replayserve}" VENV_ROOT="${VENV_ROOT:-/tmp/wjh/venvs/vllm-0.20.0-cu129-profiler-v1}"