Commit Graph

Select branches

Hide Pull Requests

cch/megamoe-rc-v0.1

Mono Color

• 37f3325b06 [router][grpc] Support E2E non-stream chat completions (#10980) Chang Su 2025-09-26 22:02:06 -07:00
• bd95944cf6 [Bugfix][Minor][Benchmark] Fix some bugs due to PR #10495 (#10982) Muqi Li 2025-09-27 13:01:05 +08:00
• c8a5d12abe [HiCache]: Support dynamic loading backends for hicache (#10551) hzh0425 2025-09-27 09:34:11 +08:00
• 2387c22b56 Ci monitor support performance (#10965) Xiaoyu Zhang 2025-09-27 09:11:21 +08:00
• 592ddf374f Add simple docker file for B300 (#10944) hlu1 2025-09-26 17:26:57 -07:00
• 0c3db88978 [router][grpc] Add helpfer functions for decoder in router.rs and fix specs (#10971) Chang Su 2025-09-26 17:10:45 -07:00
• 2bdaf482f9 refactor loading weights from remote instance coding format (#10941) amysaq2023 2025-09-27 06:25:39 +08:00
• 777eb53897 ci: refactor nightly test (#10495) Mick 2025-09-27 06:24:30 +08:00
• 05a3526654 Restruct gpu_memory_settings in a unify function and relax max_cuda_graph_bs (#10372) Xiaoyu Zhang 2025-09-27 06:10:49 +08:00
• e56c64bfaf Update label field comment to indicate deprecation (#10970) Lianmin Zheng 2025-09-26 12:59:59 -07:00
• fff7fbabe6 ci: fix rate-limit of huggingface with hf auth login (#10947) Mick 2025-09-27 02:02:44 +08:00
• aae7ead2d0 [router] remove old/oudated/useless comments across code base (#10968) Simo Lin 2025-09-26 13:48:50 -04:00
• a7fe6e10a1 [router] remove old/oudated/useless comments (#10967) Simo Lin 2025-09-26 12:45:15 -04:00
• be059b83d6 [router] grpc router regular mode import cleanup (#10963) Simo Lin 2025-09-26 07:06:59 -04:00
• 5d4fe1ceee [router] add move grpc worker management from router to worker manager (#10960) Simo Lin 2025-09-26 06:57:57 -04:00
• 1b011e68dc [router] move grpc client from router to worker and builder (#10958) Simo Lin 2025-09-26 06:13:47 -04:00
• 5c0efa562b [router]fix code owner syntax error (#10956) Simo Lin 2025-09-26 06:07:18 -04:00
• 1e57b9472d [router] add grpc client get and set (#10955) Simo Lin 2025-09-26 06:07:05 -04:00
• a5095d6262 Fuse write kv buffer into rope for qwen3 moe & bailing moe (#10749) Yuan Luo 2025-09-26 15:18:41 +08:00
• 6c2c467d77 [router] update owners for router components (#10927) Simo Lin 2025-09-26 02:46:46 -04:00
• c3d2ad4ee6 CI: Fix docker manifest build (#10936) Sahithi Chigurupati 2025-09-25 23:22:55 -07:00
• 7ec5b4e89c [PD-HiCache]: Support Async Offloading KVCache In Decode Side (#10192) hzh0425 2025-09-26 14:20:49 +08:00
• 6088548216 Update CODEOWNERS to include JustinTong0323 in FC (#10939) Xinyuan Tong 2025-09-25 22:55:56 -07:00
• 172bcf0152 Revert "Refactor kv_cache_scheme handling for quantization (#10132)" (#10935) Yineng Zhang 2025-09-25 20:14:15 -07:00
• 37158f2018 router: Support parallel sampling num > 1 in grpc_server and non-stream handling (#10929) Chang Su 2025-09-25 20:03:35 -07:00
• 3e95aa1a09 Remove pull_request trigger from CI monitor workflow (#10932) Lianmin Zheng 2025-09-25 19:40:38 -07:00
• c4197e99bb [ci] add ci-monitor workflow (#10898) Xiaoyu Zhang 2025-09-26 10:29:47 +08:00
• 0ac6114694 Replace the Kimi-K2 generated tool call idx with history tool call count (#10612) eraser00 2025-09-26 09:47:40 +08:00
• 7dcd689b47 [router][refactor] Clean up protobuf fields (#10923) Chang Su 2025-09-25 17:48:47 -07:00
• f7bab41a29 [router] change log level to warning (#10926) Simo Lin 2025-09-25 20:32:59 -04:00
• f68dd998b9 Rename customer label -> custom label (#10899) Lianmin Zheng 2025-09-25 16:19:53 -07:00
• 35ec2a45a8 [minor] Remove deprecated function get_ip (#10883) Lianmin Zheng 2025-09-25 16:18:04 -07:00
• 0035f1cefa fix env flashinfer (#10910) Swipe4057 2025-09-26 01:44:48 +03:00
• 5e21d6aec0 refactor: Move grpc/client.rs to grpc_client/sglang_scheduler.rs (#10924) Chang Su 2025-09-25 14:21:22 -07:00
• cd4da1f19b Refactor kv_cache_scheme handling for quantization (#10132) Mohammad Miadh Angkad 2025-09-26 01:32:15 +08:00
• 916784746b router: Fix constraint proto and build_constraint in grpc router (#10881) Chang Su 2025-09-25 08:12:06 -07:00
• d511b2d905 [router] consolidate worker load monitoring (#10894) Simo Lin 2025-09-25 09:59:30 -04:00
• 77830a265e Add fuse_moe per-channel tune (#10915) lukec 2025-09-25 21:12:09 +08:00
• fce170480a integrate AIBrix KVcache (#10376) yi wang 2025-09-25 14:47:09 +08:00
• 3d40794fcf [HiCache] Cleaning the deprecated host memory state (#10778) Zhiqiang Xie 2025-09-24 23:43:53 -07:00
• c1f39013b7 [ci feature] add ci monitor (#10872) Xiaoyu Zhang 2025-09-25 14:16:29 +08:00
• 3e43eb137b [Auto Sync] Update model_config.py (20250925) (#10885) Lianmin Zheng 2025-09-24 22:59:16 -07:00
• 458c0219a6 [router] simplify tokenizer dev doc (#10895) Simo Lin 2025-09-25 01:15:56 -04:00
• a73eb8cd20 [router] Support Oracle DB(ATP) Data Connector (#10845) Keyang Ru 2025-09-24 20:59:32 -07:00
• e738703547 [router] consolidate worker get loads (#10880) Simo Lin 2025-09-24 22:13:31 -04:00
• fe531d6f4e [Bug] Fix Issue#10215 (#10572) Yuhao Yao 2025-09-25 09:51:50 +08:00
• c4e314f986 Restruct sgl-kernel benchmark (#10861) Xiaoyu Zhang 2025-09-25 07:45:25 +08:00
• 7a06ef984d [router] consolidate health endpoints and flush cache (#10876) Simo Lin 2025-09-24 18:23:21 -04:00
• 4a87ba217f router-grpc: Add tools processing and other paramters for apply_chat_template (#10877) Chang Su 2025-09-24 15:23:06 -07:00
• d7b20dd65d chore: Initial support for input config files (#10534) kushanam 2025-09-24 14:45:52 -07:00
• c3faf2d6e6 [router] select first healthy worker on proxied get requests (#10827) luna 2025-09-24 15:45:41 -03:00
• 9209b209be router-grpc: Support jinja chat template content format detection (#10832) Chang Su 2025-09-24 11:45:01 -07:00
• adba172fd1 ci: free space on workers for build (#10786) ishandhanani 2025-09-24 17:58:22 +08:00
• cd641a995c fix bailing_moe with enable_dp_attention (#10860) GuoweiWangU 2025-09-24 17:29:32 +08:00
• 71f24ef8f6 feat: add cache_salt support to request (#10718) Xinyuan Tong 2025-09-23 23:30:25 -07:00
• b1f0fc1c0b Add CI timeout guidelines (#10829) Lianmin Zheng 2025-09-23 22:08:02 -07:00
• 32d893730f Revert "[fix][pd-disag]no need set next batch sampling info done in prefill" (#10828) Lianmin Zheng 2025-09-23 17:02:01 -07:00
• f47a2c67e6 [Auto Sync] Update load_config.py, model_config.py, configu... (20250923) (#10825) Lianmin Zheng 2025-09-23 16:48:12 -07:00
• ee704e6265 [router] add auth middleware for api key auth (#10826) Chang Su 2025-09-23 16:07:34 -07:00
• f4e3ebeb05 [router] Support streaming for Openai Router Response api (#10822) Keyang Ru 2025-09-23 14:56:28 -07:00
• 312bfc4c95 [Auto Sync] Update simple_eval_common.py (20250923) (#10824) Lianmin Zheng 2025-09-23 13:50:47 -07:00
• e290303ea1 [Auto Sync] Update elementwise.py (20250923) (#10823) Lianmin Zheng 2025-09-23 13:50:22 -07:00
• aab35bccb4 fix: draft model IMA by overide max_positional_embeddings (#10787) Xinyuan Tong 2025-09-23 12:56:16 -07:00
• 42aedb02af [Auto Sync] Update protocol.py (20250923) (#10820) Yineng Zhang 2025-09-23 12:49:56 -07:00
• 984730b732 add tunning files for QWEN-3-NEXT (#10794) Yiakwy 2025-09-24 03:46:30 +08:00
• 23632d350c Fix latest main ci (#10799) Shangming Cai 2025-09-24 03:46:13 +08:00
• 08b8c0c3cd [router] fix axum default body limit (#10818) Chang Su 2025-09-23 12:44:17 -07:00
• d42975c641 Remove duplicate code in qwen2 model (#10540) Lzhang-hub 2025-09-24 02:40:51 +08:00
• adc24a3a0c fix ceval (#10504) ZhengHSI 2025-09-24 02:35:25 +08:00
• 7ff93e613f router(grpc): Implement route for chat_cmpl endpoint (#10761) Chang Su 2025-09-23 11:26:33 -07:00
• b24b2e7ed7 [router] use dashmap for radix tree instead of hash for multi model (#10814) Simo Lin 2025-09-23 14:25:53 -04:00
• 7135db5d31 [ROCm] Update aiter to v0.1.5.post3 (#10812) sogalin 2025-09-24 01:54:12 +08:00
• 4b5ef3002c [fix][pd-disag]no need set next batch sampling info done in prefill (#10259) Jimmy 2025-09-24 01:24:36 +08:00
• 4f564b9e83 model: support qwen3-vl series (#10323) Zheng Li 2025-09-24 01:15:52 +08:00
• 98c3b04ff2 [router] responses api POST and GET with local storage (#10581) Simo Lin 2025-09-23 12:12:02 -04:00
• ddab4fc7c7 [router] fix cache aware routing strategy and lock contention (#10773) Simo Lin 2025-09-23 11:53:49 -04:00
• d21c35224d Fix hicache mooncake backend CI (#10792) Shangming Cai 2025-09-23 17:04:44 +08:00
• 4a762041d7 move environ into sglang.srt to avoid break SRT auto sync. (#10791) Liangsheng Yin 2025-09-23 17:04:20 +08:00
• ea338676b5 Clean up server args (#10770) Lianmin Zheng 2025-09-23 00:22:32 -07:00
• b06db198ba followup: clean up dockerfiles and release yamls (#10783) ishandhanani 2025-09-23 15:19:46 +08:00
• 8c1ef0f914 chore: upgrade sgl-kernel 0.3.12 (#10782) Yineng Zhang 2025-09-23 00:18:54 -07:00
• f5a2faf2b8 Introduce FutureMap (#10715) Liangsheng Yin 2025-09-23 14:27:30 +08:00
• 1c82d9db28 feat: unify dockerfiles (#10705) ishandhanani 2025-09-23 14:23:48 +08:00
• 9241f4fd20 Move cached kernel to srt.utils (#10776) Lifu Huang 2025-09-22 23:00:36 -07:00
• 063c3791fe Fix trtllm_mla slow concat kernel in MTP (#10777) fzyzcjy 2025-09-23 13:47:49 +08:00
• 632b7d8cc9 Use simulate acc len from sglang.environ (#10771) Liangsheng Yin 2025-09-23 12:59:50 +08:00
• 16adf3dcab [router] fix logger type mismatch (#10774) Chang Su 2025-09-22 21:02:28 -07:00
• c3a1d7759f [router] remove pd router draining channel (#10767) Simo Lin 2025-09-22 23:49:33 -04:00
• 89971c4c3c [router] refactor router and worker management 4/n (#10756) Simo Lin 2025-09-22 21:35:10 -04:00
• 113f8f65a2 [Auto Sync] Update configurer.py (20250923) (#10765) Lianmin Zheng 2025-09-22 17:34:34 -07:00
• e22f3a5ec9 [Ascend]optimize Qwen3 on Ascend (#10574) ronnie_zheng 2025-09-23 03:18:36 +03:00
• 095093ee5a [Ascend] optimize Qwen-vl on Ascend (#10556) ronnie_zheng 2025-09-23 03:18:16 +03:00
• d27a6f7092 [Feature] Add MLAProcess for DeepSeek MLA on NPU (#10130) Even Zhou 2025-09-23 08:17:48 +08:00
• 0753ef831e [Auto Sync] Update flashattention_backend.py (20250922) (#10762) Yineng Zhang 2025-09-22 16:41:42 -07:00
• 662393f27d fix: kv events with tp > 1 (#10541) ishandhanani 2025-09-23 06:55:44 +08:00
• b1bb8e7490 Enables TRT-LLM backend to be used for target_verify (#10281) pranavm-nvidia 2025-09-22 15:54:00 -07:00
• 38c00ed7a1 Fix multimodal registry and code sync scripts (#10759) Lianmin Zheng 2025-09-22 15:36:01 -07:00
• d4041a5eeb refactor zero copy (#10300) pansicheng 2025-09-23 06:17:31 +08:00
• 2f555c4cee [Generative Score API] Added test_scores_api.py to github CICD to run per commit (#10755) Vedant Jhaveri 2025-09-22 14:41:57 -07:00
• e53df7c009 chore: bump sgl-kernel v0.3.12 (#10732) Yineng Zhang 2025-09-22 14:39:25 -07:00