Files
vllm-omni/docs/design/module/profiling.md
T
2026-07-16 12:08:45 +08:00

1.2 KiB

title, kind, status, owners, primary_code_paths, related_code_paths, depends_on, validation_paths, upstream_refs, last_reviewed
title kind status owners primary_code_paths related_code_paths depends_on validation_paths upstream_refs last_reviewed
Profiling module draft
@gcanlin
vllm_omni/profiler/**
vllm_omni/diffusion/profiler/**
vllm_omni/entrypoints/**
observability.md
tests/profile/**
vllm.profiler
2026-07-16

Profiling

Profiling owns opt-in instrumentation and trace collection used to locate runtime bottlenecks without changing model results or execution policy.

Candidate invariants

PROFILE-INV-001: Profiling is opt-in

Rule: Expensive trace collection MUST be disabled by default and bounded by an explicit start and stop lifecycle.

PROFILE-INV-002: Instrumentation preserves semantics

Rule: Profiling MUST NOT change scheduling decisions, generated outputs, or resource ownership beyond documented synchronization overhead.

PROFILE-INV-003: Trace context is sufficient

Rule: Trace events SHOULD identify stage, rank, worker, operation, and request where available without embedding user payloads.

Safe-change guide

Test disabled overhead, repeated start and stop, cleanup, multi-rank trace naming, and each supported profiler backend.