[core] Always-on StreamingSession in UnifiedRadixCache#23202
Merged
Conversation
…ng-session # Conflicts: # python/sglang/srt/session/session_controller.py
Contributor
|
Warning You have reached your daily quota limit. Please wait up to 24 hours and I will start processing your requests again! |
UnifiedRadixCache
UnifiedRadixCacheStreamingSession in UnifiedRadixCache
Collaborator
Author
|
/tag-and-rerun-ci |
23 tasks
zhangying098
pushed a commit
to zhangying098/sglang
that referenced
this pull request
Apr 23, 2026
kyx1999
pushed a commit
to KMSorSMS/sglang
that referenced
this pull request
Apr 27, 2026
Merged
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Stacked on #23145.
Summary
StreamingSession(renamed fromSessionAwareCache) inUnifiedRadixCacheunconditionally -- thetry_*entries short-circuit on non-streaming reqs / realTreeNodes, so there is zero overhead when no streaming session is actually openedenable_streaming_sessionplumbing forUnifiedRadixCacheChanges
Rename
session/session_aware_cache.py→session/streaming_session.pySessionAwareCache→StreamingSession. The class still extendsBasePrefixCachefor wrapper-mode ergonomics (tree_cache = StreamingSession(RadixCache(...))), but its identity is "a streaming session component that also satisfies the cache interface" rather than "a cache variant"Always-on embedding
CacheInitParams: drop theenable_streaming_sessionfield (no longer plumbed)UnifiedRadixCache.__init__: unconditionally constructself.session = StreamingSession(inner=self)(type is no longerOptional)if self.session is not Noneguards in dispatch methods (match_prefix/cache_finished_req/cache_unfinished_req/inc_lock_ref/dec_lock_ref),reset,sanity_check,release_session, andsession_held_*supports_streaming_session()now returnsTrueScheduler: removeparams.enable_streaming_session = server_args.enable_streaming_sessionplumbing