Gahow Wang 18f1bd4240 Update MEETING.md + PAPER_OUTLINE.md with connector_tax substrate validation ...

2026-05-27 trace-replay A/B/C (commit ef9e010) shows the kv_both substrate
is net positive on current codebase, not just neutral:
  - TTFT p90: 11.97s plain → 9.74s kv_both (−18.6%) → 7.58s with DR-fix (−36.6%)

This reverses the elastic_migration_v2 paper's +45% kv_both penalty claim
and removes the primary cause of the 4 prior migration reverts.

Reframes EAR Pillar 2 from "DEFERRED" to "PARTIAL" — substrate verified,
e2e strategy-layer validation (trigger thresholds + target selection in
the dispatch-coupling feedback loop) remains as the only open risk.

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

2026-05-27 09:17:31 +08:00

analysis

Add NIXL substrate isolation control + attribution decomposition

2026-05-26 16:02:12 +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

Use PNG for KV memory wall figure; switch outline to inline image embeds

2026-05-27 09:13:26 +08:00

microbench

Connector tax: trace-replay confirms +45% kv_both penalty is gone; DR-fix adds 22% more

2026-05-27 09:13:50 +08:00

patches

Add vLLM patches directory for version-controlled patch management

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

replayer

EAR outline: copy reusable figures, mark migration sections deferred

2026-05-27 01:44:13 +08:00

scripts

Fix review P2s: lockfile, model path convention, trap robustness

2026-05-26 16:05:43 +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

A3: vLLM scheduler patch for step-level JSONL log

2026-05-25 16:19:11 +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

MEETING.md

Update MEETING.md + PAPER_OUTLINE.md with connector_tax substrate validation

2026-05-27 09:17:31 +08:00

PAPER_OUTLINE.md

Update MEETING.md + PAPER_OUTLINE.md with connector_tax substrate validation

2026-05-27 09:17:31 +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

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%