Gate tiny CP shared-KV prefetch by token threshold

Prefix materialize prefetch has fixed launch and coordination overhead, so tiny cache-hit prefixes should stay on the simpler synchronous path. The default threshold is now expressed as a cached import-time token threshold while the existing page override remains available for workload-specific tuning.

Both MLA and index prefix prefetchers use the same page-size-aware threshold, so CP shared-KV prefix prefetch is enabled only when the prefix covers at least one page per CP lane and at least the configured token threshold.

Constraint: The default token threshold must be read once to avoid hot-path env lookups

Constraint: Existing page threshold override must continue to disable or force the gate

Rejected: Hard-code 1024 tokens | tuning needs to be possible without code changes

Rejected: Read token threshold on every maybe_create call | unnecessary hot-path env lookup

Confidence: medium

Scope-risk: narrow

Directive: Keep MLA and index prefetch threshold logic shared; do not let their gates diverge

Tested: Not rerun per user request; prior py_compile, diff check, and isolated env-cache check had passed before commit

Not-tested: full pytest in local environment due missing optional dependencies/kernel import constraints

Not-tested: GLM5 E2E throughput after this threshold change
This commit is contained in:
laoyao0822
2026-05-28 08:57:45 +08:00
parent 25f2147677
commit 26c792939d
4 changed files with 64 additions and 17 deletions
+1
View File
@@ -212,6 +212,7 @@ class Envs:
SGLANG_CP_SHARED_KV_ENABLE_MLA_PREFETCH = EnvBool(False)
SGLANG_CP_SHARED_KV_LOG_MLA_PREFETCH = EnvBool(False)
SGLANG_CP_SHARED_KV_MATERIALIZE_NVTX = EnvBool(False)
SGLANG_CP_SHARED_KV_MLA_PREFETCH_MIN_PREFIX_TOKENS = EnvInt(1024)
SGLANG_CP_SHARED_KV_MLA_PREFETCH_MIN_PREFIX_PAGES = EnvInt(-1)
SGLANG_CP_DRAFT_SHARED_KV = EnvBool(False)
SGLANG_CP_DRAFT_SHARED_KV_DEBUG = EnvBool(False)