6d1c9237fa
After E3 exposed massive session-level eviction (90 trims × avg
67K tokens/evict = 6.1M tokens trashed in 1h12min), we have to
acknowledge the local-patch sequence (E2→load-floor→Fix A →
proposed disable-migration → proposed disable-admission) was a
KVC-to-DP collapse trajectory, not a fix.
The fundamental issue: SessionAwareCache merged two responsibilities
that should be separate.
1. Session lifecycle tracking (legitimate — streaming sessions
reuse KV across turns and need per-session metadata).
2. Eviction granularity decision (wrong — sessions should not be
the eviction unit).
`release_session` frees the session-exclusive range
[cache_protected_len, kv_allocated_len), which is the post-radix-
commit tail accumulated over decode/extend. On Inferact's
50-session workload this is 35-87K tokens per session. The radix
tree never gets a chance to do block-level leaf-LRU on that range
because it was never committed there.
Effect: evict-revisit cycle forces full 50-90K re-prefill per
session per evict — which is exactly the per-request cost of naive
PD-disagg. KVC's direct-to-D fast-path advantage collapses.
The right fix is structural (not a patch): progressively commit
streaming-session decode output to the radix tree so SGLang's
block-level LRU can shed only the deepest leaves, preserving the
recent prefix that next-turn requests are most likely to match.
SessionSlot becomes pure metadata. Scope is ~1-2 weeks of vendored
SGLang refactor, orthogonal-and-complementary to the D→P sync work
proposed in RESEED_SLOW_PATH_AND_D_TO_P_GAP §4.
Doc lists five anti-patterns the next agent should avoid (tuning
migration_reject_threshold, disabling migration/admission, etc) —
all of those are local symptoms downstream of the eviction
granularity choice.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Agentic PD Hybrid
这个项目是在 SGLang xPyD 上做一个最小实验框架，用来判断：
面向 agentic coding workload 的 session-aware / KV-cache-aware P/D routing，能不能降低端到端延迟。
更完整但仍然简洁的说明见 docs/PROJECT_OVERVIEW.md。
当前做了什么
- 启动单机 SGLang P/D 栈。
- 回放 Ali coding agent trace，并记录 request-level metrics。
- 支持
default、sticky、kv-aware路由策略。 - 支持
pd-disaggregation、kvcache-centric、pd-colo对比。 - 支持小 append、多轮 session 的 micro-benchmark trace。
- 维护了基于 SGLang
v0.5.10的本地 patch，放在third_party/sglang。
环境
统一使用 uv：
uv sync
默认模型路径：
~/models/Qwen/Qwen3-Coder-30B-A3B-Instruct
当前主要测试环境是单机 8 GPU，约束是 prefill + decode <= 8。
常用命令
生成小 append trace：
uv run agentic-pd-hybrid make-small-append-trace \
--output outputs/smoke-hotcap-30k-1k-256.jsonl \
--session-count 4 \
--turns-per-session 3 \
--initial-input-length 30000 \
--append-input-length 1000 \
--output-length 256
跑 live benchmark：
uv run agentic-pd-hybrid benchmark-live \
--trace outputs/micro-serveable-varturn-30k-1k-256-20260424T0756Z.jsonl \
--output-root outputs/live-serveable-varturn-30k-1k-256-hotcap \
--mechanism kvcache-centric \
--policy kv-aware \
--kvcache-admission-mode worker \
--prefill-workers 1 \
--decode-workers 1 \
--prefill-gpu-ids 0 \
--decode-gpu-ids 1 \
--transfer-backend mooncake \
--target-duration-s 2000 \
--session-sample-rate 1.0 \
--min-turns 2 \
--time-scale 1 \
--concurrency-limit 1000
只回放并写 metrics：
uv run agentic-pd-hybrid replay \
--trace path/to/trace.jsonl \
--policy kv-aware \
--mechanism pd-disaggregation \
--router-url http://127.0.0.1:8000 \
--output outputs/replay.jsonl
输出
每次 replay/benchmark 会写：
- request metrics：
request-metrics.jsonl - 汇总结果：
request-metrics.jsonl.summary.json
重点看：
- E2E latency
- TTFT / TPOT
- execution mode
- cached tokens
- KV transfer blocks
- error
维护约定
- 项目代码改动：
feat:/fix:/docs:。 - SGLang 改动：
feat(sglang): .../fix(sglang): ...。 third_party/sglang的基线是 clean SGLangv0.5.10snapshot。- 不提交
outputs/、日志、__pycache__、虚拟环境。