Gahow Wang 48ae72467a Replayer: closed-loop inter-turn think-time mode ...

Add --inter-turn-think (env REPLAY_INTER_TURN_THINK_S): turn 1 fires on
session admission, each later turn a FIXED think-time after the previous
turn COMPLETES, ignoring absolute trace timestamps. Combined with
--max-inflight-sessions (env REPLAY_MAX_INFLIGHT) this is a stable N-user
closed loop, removing the open-loop "fire immediately because timestamp is
in the past" retrigger artifact. Needed for the dispatch-coupling
(wall-clock amplification) sweep.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

2026-05-29 18:19:12 +08:00

analysis

Add leastwork_kappa decode-aware ablation (net-negative, documented)

2026-05-29 17:07:23 +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

figs

PD_DISAGG_RESULTS §6.3: producer hot-pinning figure

2026-05-29 00:38:20 +08:00

microbench

600s-truncated trace + LPWL 5-policy results

2026-05-29 16:08:35 +08:00

patches

Add vLLM patches directory for version-controlled patch management

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

replayer

Replayer: closed-loop inter-turn think-time mode

2026-05-29 18:19:12 +08:00

scripts

Add leastwork_kappa decode-aware ablation (net-negative, documented)

2026-05-29 17:07:23 +08:00

tests

unified_v2.1: relax gates + add unified_kv_both isolation control

2026-05-26 10:40:57 +08:00

third_party/vllm

Gate evict_sent_blocks behind VLLM_EVICT_SENT_BLOCKS

2026-05-29 18:18:59 +08:00

traces

600s-truncated trace + LPWL 5-policy results

2026-05-29 16:08:35 +08:00

.gitignore

600s-truncated trace + LPWL 5-policy results

2026-05-29 16:08:35 +08:00

FIXES.md

Add FIXES.md with prioritized repo cleanup checklist

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

MEETING.md

§2.3 reframe: dispatch coupling is regime-dependent, not binary chatbot/agentic

2026-05-27 16:51:38 +08:00

PAPER_OUTLINE.md

§2.3 reframe: dispatch coupling is regime-dependent, not binary chatbot/agentic

2026-05-27 16:51:38 +08:00

pyproject.toml

Fix review bugs: PD-sep counter leaks, hardcoded paths, missing deps

2026-05-26 15:54:55 +08:00

REPORT.md

Docs: reconcile routing docs with current hybrid direction

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

RESULTS_SUMMARY.md

Correct PD-disagg cost/benefit framing across repo

2026-05-27 22:04:49 +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 review P2s: lockfile, model path convention, trap robustness

2026-05-26 16:05:43 +08:00

Description

No description provided

48 MiB

Languages

Python 82.9%

Shell 17.1%