Gahow Wang d57e338366 A1: replayer instrumentation for cross-process join ...

RequestMetrics gains absolute unix timestamps (t_dispatch_unix,
t_first_token_unix, t_finish_unix), the proxy_request_id, the chosen
endpoint URL, and the trace hash_ids. Replayer sends
X-Request-Id: <session_id>:<turn_id>:<chat_id>:<idx> so proxy
breakdown rows can be joined to metrics by exact key.

Required by Batch 0 (online sequentiality proof) and Batch 1 reuse
decomposition; existing metrics.jsonl couldn't establish either.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

2026-05-25 16:18:52 +08:00

analysis

Characterization plan: progress snapshot + Claude work plan

2026-05-25 16:18:41 +08:00

docs

Docs: reconcile routing docs with current hybrid direction

2026-05-25 10:47:14 +08:00

experiments

Add elastic PS evaluation plan for production-realistic trace

2026-05-23 15:56:05 +08:00

patches

Add vLLM patches directory for version-controlled patch management

2026-05-22 00:26:14 +08:00

replayer

A1: replayer instrumentation for cross-process join

2026-05-25 16:18:52 +08:00

scripts

PD-sep matrix infrastructure: bench.sh pdsep mode + matrix driver

2026-05-25 11:47:33 +08:00

tests

A1: replayer instrumentation for cross-process join

2026-05-25 16:18:52 +08:00

third_party/vllm

Evict migrated blocks from prefix cache after KV send completes

2026-05-24 16:56:34 +08:00

.gitignore

Phase 1 milestone: system-level analysis + reproducible report

2026-05-22 16:17:41 +08:00

FIXES.md

Add FIXES.md with prioritized repo cleanup checklist

2026-05-23 20:35:56 +08:00

pyproject.toml

tests: add minimal coverage for percentile + proxy routing (S1)

2026-05-23 21:07:14 +08:00

REPORT.md

Docs: reconcile routing docs with current hybrid direction

2026-05-25 10:47:14 +08:00

TODO.md

LMetric routing policy (OSDI'26) + A/B results vs linear baseline

2026-05-22 16:57:32 +08:00

uv.lock

Fix NONE_HASH import: use module ref instead of from-import (value binding bug)

2026-05-24 01:32:19 +08:00

Description

No description provided

48 MiB

Languages

Python 82.9%

Shell 17.1%