Commit Graph

224 Commits

Author SHA1 Message Date
fzyzcjy
9c2530642c Change routing policy API to be async to support more policies (#17048) 2026-01-17 17:12:51 +08:00
fzyzcjy
305c1a575a Tiny remove unused code (#17047) 2026-01-17 11:58:43 +08:00
fzyzcjy
c824ddd581 Fix imbalancedness for manual policy min group mode for requests without routing id (#17044) 2026-01-17 11:58:35 +08:00
Chang Su
4229de3b13 [model-gateway] Refine TokenizerRegisty.load() to handle duplication (#17230) 2026-01-16 13:53:21 -08:00
Chang Su
a7f5677abe refactor: unify registration through tokenizer_registration workflow (#17187) 2026-01-16 10:53:36 -08:00
Chang Su
669d309a8b [model-gateway] Consolidate "unknown" model id usage (#17186) 2026-01-15 21:02:40 -08:00
jeff.ye
c020d30045 [Model-Gateway: grpc]: create tokenizer with chat template (#17052)
Signed-off-by: jeff.ye <jeff.ye@novita.ai>
2026-01-14 17:56:08 -08:00
Simo Lin
f091858304 [gRPC] Add GetLoads RPC for comprehensive load metrics (#17087) 2026-01-14 12:05:10 -08:00
Ziwen Zhao
cf25852a1d [model-gateway] add --disable-health-check option to skip worker health probes (#17002) 2026-01-13 17:28:32 -08:00
Tony Lu
5938c3b06a [model-gateway] HA - Lightweight State Layer + gRPC Mesh (#14108)
Signed-off-by: Kun(llfl) <i@imux.top>
Signed-off-by: Tony Lu <tonylu@linux.alibaba.com>
Co-authored-by: Kun(llfl) <i@imux.top>
2026-01-13 17:03:39 -08:00
Praneth Paruchuri
250477d2ac [model-gateway] Optimize L1 cache insertion with incremental hashing and tokenization (#16259)
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
Co-authored-by: Simo Lin <linsimo.mark@gmail.com>
2026-01-13 06:24:25 -08:00
fzyzcjy
ff3ddb9d9b Support min num routing keys in key-based load balancing policy (#16564) 2026-01-12 21:38:03 -08:00
fzyzcjy
9d3018f484 Support min load besides random routing key assignment policy in ManualPolicy (#16767) 2026-01-12 18:31:18 -08:00
fzyzcjy
1f0e3d7fd8 Support tracking worker routing key loads in gateway (#16765) 2026-01-13 08:07:17 +08:00
Simo Lin
c6a64e9f69 [smg] fix type complexity for workflow run_if (#16981) 2026-01-12 15:41:52 -08:00
Simo Lin
e0ac559ae1 feat(workflow): add scheduled/delayed steps and conditional branching (#16980) 2026-01-12 15:06:12 -08:00
Simo Lin
6620548fd8 [model-gateway] make StateStore trait async for external persistence (#16979) 2026-01-12 12:55:59 -08:00
Simo Lin
6e158e55b4 [model-gateway] improve workflow engine code quality (#16977) 2026-01-12 12:14:46 -08:00
Simo Lin
ed729d22b3 [model-gateway] refactor workflow engine from type erasure to typed engines (#16973) 2026-01-12 10:47:00 -08:00
Simo Lin
fa51b85466 [model-gateway] convert workflow system to type-safe workflow data (#16970) 2026-01-12 10:06:36 -08:00
Simo Lin
d0092decb1 [model-gateway] Fix workflow engine race conditions and add graceful shutdown (#16963) 2026-01-12 06:37:39 -08:00
Wenyi Xu
c54c70ab62 [model-gateway] Improve Health Check Logging (#16930) 2026-01-11 23:01:29 -08:00
fzyzcjy
38b30c7b56 Tiny refactor age computation in router (#16850)
Co-authored-by: Simo Lin <linsimo.mark@gmail.com>
2026-01-11 21:42:43 -08:00
fzyzcjy
a1c48943d7 Tiny fix NoAvailableWorkers being a RetryError (#16896) 2026-01-11 18:53:17 -08:00
ybyang
503c3d9566 [model-gateway]: add qwen coder tool parser support xml format for qwen3 coder and microthinker (#12909) 2026-01-11 16:09:41 -08:00
Wenyi Xu
3c16c58619 [model-gateway] Add Redis support as a history backend (#16300) 2026-01-11 01:03:00 -08:00
Simo Lin
7c25687c9b fix(gateway): rewrite gauge_histogram.rs for zero-allocation hot path (#16878) 2026-01-10 18:15:21 -08:00
fzyzcjy
1f9d4795a9 Tiny add gauge histogram abstraction for engine and router (#16848) 2026-01-10 11:45:25 +08:00
Praneth Paruchuri
bd1afeb568 [model-gateway] Restore response streaming by optimizing WASM middleware buffering (#16804) 2026-01-09 09:29:22 -08:00
fzyzcjy
9e3a032ad6 [smg] cleanup router RAII guards (#16560) 2026-01-08 16:39:53 -08:00
Simo Lin
1bc7aa5801 [smg] update gRPC proto to match upstream changes (#16764)
Co-authored-by: Chang Su <chang.s.su@oracle.com>
2026-01-08 16:33:09 -08:00
Simo Lin
8726d30cb2 [smg] Add Nemotron Nano V3 reasoning parser support (#16763) 2026-01-08 16:29:24 -08:00
Ziwen Zhao
b5a94f8a8e [model-gateway] Fix IGW routing for external OpenAI workers (#16633) 2026-01-07 08:15:23 -08:00
fzyzcjy
3be1e734ee [model-gateway] extract header extraction in policy and add (#16566) 2026-01-06 20:18:44 -08:00
Chang Su
fb5b71d015 [router][openai] Rename prepare_mcp_payload_for_streaming and patch_streaming_response_json (#16596) 2026-01-06 16:33:29 -08:00
Chang Su
05b54b6d7b [router][grpc] Replace Vec<(String, String, String)> with ExtractedToolCall (#16598) 2026-01-06 16:32:59 -08:00
Chang Su
4f443f445a [model-gateway][cleanup] Fix wrong comment in manager.rs (#16601) 2026-01-06 16:32:37 -08:00
Simo Lin
d57d8e7e5f [smg] clean up logs in mcp (should be info instead warn) (#16591) 2026-01-06 12:44:32 -08:00
Chang Su
21da2dc1ce [grpc] Unify ResponsesContext and HarmonyResponsesContext (#16549) 2026-01-06 07:28:06 -08:00
Chang Su
9bf76c11a9 [responses API] Add list_tools_for_servers and threading server_keys in routers (#16540) 2026-01-05 22:42:22 -08:00
Chang Su
4cf2bbd084 [router] Remove deadcode and add note for unused API completeness methods (#16528) 2026-01-05 19:53:28 -08:00
Chang Su
b98bd9a5fb [model-gateway] Tighten visibility in modules and remove unused re-exports (#16524) 2026-01-05 17:38:50 -08:00
Chang Su
1751c75b5d [model-gateway] Tighten visibility across data_connector and grpc module (#16516) 2026-01-05 12:31:32 -08:00
Chang Su
51541404f8 [grpc] Refactor openai module (#16511) 2026-01-05 11:39:33 -08:00
Chang Su
5a2b1ed407 [grpc] Refactor grpc/regular/responses (#16509) 2026-01-05 10:21:34 -08:00
Chang Su
454dc9e242 [model-gateway][grpc] Refactor harmony/responses.rs (#16508) 2026-01-05 10:21:05 -08:00
fzyzcjy
1e41069ad1 Fix age bucket rendering issue (#16492) 2026-01-05 09:29:14 -08:00
Praneth Paruchuri
b12258bfaa [model-gateway] Optimize HTTP Router Fan-out: Replace Serial Execution with Concurrent Streams (#16042) 2026-01-04 23:38:45 -08:00
Ratish P
f02d82211a [model-gateway]: move PD configuration conflict checks to model gateway (#16088) 2026-01-05 14:16:07 +08:00
Simo Lin
4436dc0f6c [model-gateway] improve lock contention and allocation in middleware (#16405) 2026-01-04 10:40:07 -08:00