Gahow Wang
d5b276180d
Workload-conditioned operator profiling on patched vLLM 0.24.0 + Qwen3-30B-A3B/H20. H1b PASS (irregular patterns carry +23-45pp R64 raggedness, 8-45% token-efficiency loss vs rectangular controls); mechanism decomposition kills the padding narrative and finds the arrival-uniformization artifact (-12.9%); cross-version churn surface shows TP2/MNS64 -29.4% across vLLM 0.20->0.24 while the argmax held. Raw Layer-1 JSONL streams (507 MB) stay on disk, git-ignored; footer sidecars and metrics are tracked. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
53 lines
2.0 KiB
Diff
53 lines
2.0 KiB
Diff
From 668cfb7e27e488454dbf09a4927b8a60d6d49b40 Mon Sep 17 00:00:00 2001
|
|
From: Gahow Wang <gahow.wang@gmail.com>
|
|
Date: Sat, 11 Jul 2026 17:32:27 +0800
|
|
Subject: [PATCH 3/5] Log the OpProf output path at startup
|
|
|
|
Assisted-by: OpenAI Codex
|
|
---
|
|
tests/v1/core/test_opprof.py | 1 +
|
|
vllm/v1/core/sched/scheduler.py | 2 ++
|
|
vllm/v1/opprof.py | 1 +
|
|
3 files changed, 4 insertions(+)
|
|
|
|
diff --git a/tests/v1/core/test_opprof.py b/tests/v1/core/test_opprof.py
|
|
index 9bfbfcc..79c1fae 100644
|
|
--- a/tests/v1/core/test_opprof.py
|
|
+++ b/tests/v1/core/test_opprof.py
|
|
@@ -336,6 +336,7 @@ def test_writer_enospc_is_exposed_and_shutdown_is_bounded(
|
|
def test_shutdown_flush_is_idempotent(tmp_path):
|
|
sched = scheduler({"decode": request(8, 9)})
|
|
rec, path = recorder(tmp_path)
|
|
+ assert rec.writer.path == path
|
|
assert emit(rec, sched, schedule_output({"decode": 1}))
|
|
rec.close()
|
|
rec.close()
|
|
diff --git a/vllm/v1/core/sched/scheduler.py b/vllm/v1/core/sched/scheduler.py
|
|
index 303c562..769a02a 100644
|
|
--- a/vllm/v1/core/sched/scheduler.py
|
|
+++ b/vllm/v1/core/sched/scheduler.py
|
|
@@ -278,6 +278,8 @@ class Scheduler(SchedulerInterface):
|
|
dp_rank=self.parallel_config.data_parallel_index,
|
|
log_stats=self.log_stats,
|
|
)
|
|
+ if self.opprof is not None:
|
|
+ logger.info("OpProf telemetry enabled: %s", self.opprof.writer.path)
|
|
|
|
self.use_pp = self.parallel_config.pipeline_parallel_size > 1
|
|
self.use_v2_model_runner = vllm_config.use_v2_model_runner
|
|
diff --git a/vllm/v1/opprof.py b/vllm/v1/opprof.py
|
|
index f0330d0..75f63de 100644
|
|
--- a/vllm/v1/opprof.py
|
|
+++ b/vllm/v1/opprof.py
|
|
@@ -68,6 +68,7 @@ class JSONLWriter:
|
|
start: bool = True,
|
|
) -> None:
|
|
self._queue: queue.Queue[Any] = queue.Queue(capacity)
|
|
+ self.path = path
|
|
self._encoder = msgspec.json.Encoder()
|
|
self._file = path.open("xb", buffering=1 << 20)
|
|
self._thread = threading.Thread(target=self._run, daemon=True)
|
|
--
|
|
2.43.0
|
|
|