Commit Graph

Select branches

Hide Pull Requests

cch/megamoe-rc-v0.1

Mono Color

• 4ea9d74a3e Simplify health check (#9034) Lianmin Zheng 2025-08-10 17:35:05 -07:00
• dd949ace23 Revert "[1/2][resubmit] sgl-kernel: Fuse routed scaling factor into m… (#9035) Yineng Zhang 2025-08-10 17:34:54 -07:00
• f2887498f0 Simplify memory pool (#9033) Lianmin Zheng 2025-08-10 17:32:28 -07:00
• 8ecf6b9d24 Support Flatten Tensor Update Weights to speed up MOE Update Weights by 20% (#8079) Stefan He 2025-08-10 16:08:59 -07:00
• 0418b9d4ea [Optimization] Update estimated_num_new_pages logic in TokenToKVPoolAllocator (#8794) YiXR 2025-08-11 07:01:51 +08:00
• e322a94d1f Reduce CI duration of test_lora_update. (#9024) Lifu Huang 2025-08-10 15:34:04 -07:00
• 2c7f01bc89 Reorganize CI and test files (#9027) Lianmin Zheng 2025-08-10 12:30:06 -07:00
• b58ae7a2a0 Simplify frontend language (#9029) Lianmin Zheng 2025-08-10 10:59:30 -07:00
• 6345069f6c [RL] Add test for /abort_request (#7626) Stefan He 2025-08-10 09:14:19 -07:00
• ce9cf35327 [router] update pyo3 version to 0.25.1 (#9022) Simo Lin 2025-08-10 06:45:51 -07:00
• f8a173bb50 Improve LoRA Perf by Deprecating FlashInfer and Eliminating Redundant Tensor Ops (#8940) Lifu Huang 2025-08-10 01:04:45 -07:00
• 6b847a9a05 Optimize: Cache CUDA device to reduce redundant calls during tensor l… (#8996) JiLi 2025-08-10 15:32:57 +08:00
• 473400e452 [router] upgrade kube version to latest (#9018) Simo Lin 2025-08-09 22:49:45 -07:00
• dd665f967f [router] upgrade rand to latest version (#9017) Simo Lin 2025-08-09 22:49:30 -07:00
• 3817a37d87 [router] upgrade to latest sgl kernel for router ci (#9019) Simo Lin 2025-08-09 21:49:18 -07:00
• 7ba5ad5766 [Fix] Fix flashinfer cpu <-> gpu synchronization (#8340) DarkSharpness 2025-08-09 20:11:40 -07:00
• 19bc77f05c [Fix] Fix hicache backend (#8991) DarkSharpness 2025-08-09 17:16:25 -07:00
• 86497d99f2 fix page first per layer pf2lf kernel (#8915) huangtingwei 2025-08-10 08:16:11 +08:00
• 5c31b35db2 [hicache] Optimization for DMA copy (#8245) cctry 2025-08-09 17:16:07 -07:00
• ef48d5547e Fix CI (#9013) Lianmin Zheng 2025-08-09 16:00:10 -07:00
• a886564a18 fix flashinfer allreduce fusion import bug (#9007) Xiaoyu Zhang 2025-08-10 04:47:05 +08:00
• 9a44b643c6 Fix CI (#9012) Lianmin Zheng 2025-08-09 13:33:42 -07:00
• 41d71ca488 fix: fix obsolete qwen-audio processor arg (#9003) Mick 2025-08-10 04:18:36 +08:00
• 20cfc5a251 [perf] add kimi-k2 b200 fused moe config (#9010) JieXin Liang 2025-08-10 03:40:49 +08:00
• 48b8b4c124 fix nvshmem cu126 (#9001) Yineng Zhang 2025-08-09 03:34:54 -07:00
• 323bc2f51a Enable TBO on ROCm (#8329) Chaitanya Sri Krishna Lolla 2025-08-09 14:29:55 +05:30
• 137e75daa1 [Feature] Optimize DeepSeek's DeepEP on Ascend NPU (#8355) Even Zhou 2025-08-09 16:35:00 +08:00
• 52e1f52f32 [bugfix] Fix missing args in bench one batch (#8877) Trevor Morris 2025-08-09 01:34:03 -07:00
• 5018809222 [DP] fix: engine crash when decode batch is padded (#8995) Cheng Wan 2025-08-09 01:29:29 -07:00
• 326a901df4 chore: upgrade sgl-kernel 0.3.3 (#8998) Yineng Zhang 2025-08-09 01:22:01 -07:00
• 6e0b646832 HiCache Storage tp fix (#8878) Zhiqiang Xie 2025-08-09 01:16:51 -07:00
• 4a9f3eef90 Tiny Llama4 type error in constructor (#6752) Brayden Zhong 2025-08-09 04:03:59 -04:00
• 1b7afad0dd feature(hicache): Support hf3fs-hicache reusing kvcache across different instances (#8673) hzh0425 2025-08-09 16:03:00 +08:00
• f29aba8c6e Support glm4.1v and glm4.5v (#8798) Binyao Jiang 2025-08-09 00:59:13 -07:00
• faa25df1ae feat: update flashinfer ar oneshot params (#8687) eigen 2025-08-09 03:51:27 -04:00
• 7b81f956eb Fix qwen2 audio not working bug (#8600) Binyao Jiang 2025-08-09 00:42:29 -07:00
• d3e67deb1b Fix redundant kernel in sink dtype conversion (#8966) fzyzcjy 2025-08-09 15:34:49 +08:00
• 442534aa44 Add CI for gpt-oss model on hopper (#8851) fzyzcjy 2025-08-09 15:34:23 +08:00
• de8b8b6e5c chore(deps): update minimum python to 3.10 (#8984) ishandhanani 2025-08-09 00:30:23 -07:00
• 3f2e315f6e optimize: reduce shulffle and quantization overhead in cutlass_moe sm90 (#8962) tql.99 2025-08-09 15:29:12 +08:00
• 6e2151183b Fix incorrect default get_hidden_dim logic (#8987) Lifu Huang 2025-08-09 00:25:38 -07:00
• a47baff12c [hotfix] use the original implementation in 8785 (#8994) Cheng Wan 2025-08-08 21:47:25 -07:00
• fd7e15b76d Revert "[bug fix] Ensure local token and global token buffers are pointing to different storage " (#8993) Cheng Wan 2025-08-08 21:34:17 -07:00
• fc42ff7b63 [Fix] Fix wrong backend chosen in hybrid backend (#8989) DarkSharpness 2025-08-08 21:21:17 -07:00
• 7c0db868a1 Molly/ci gnr server (#8667) DiweiSun 2025-08-09 11:01:16 +08:00
• 706bd69cc5 Clean up server_args.py to have a dedicated function for model specific adjustments (#8983) Lianmin Zheng 2025-08-08 19:56:50 -07:00
• 23f2afb2ce [AMD] Update SGLang image fallback logic for AMD CI (#8980) michael-amd 2025-08-08 18:51:29 -07:00
• a60f88b5a4 Add unit test for flashinfer fp4 moe (#8330) Trevor Morris 2025-08-08 17:55:37 -07:00
• 591c232f7c [1/2][resubmit] sgl-kernel: Fuse routed scaling factor into moe_fused_gate (select_experts) (#8770) Trevor Morris 2025-08-08 17:55:06 -07:00
• f352b793be Minor Optimizations in Schedule Batch (#8724) Lianmin Zheng 2025-08-08 16:10:16 -07:00
• 6642e3a295 [Fix] Add a workflow to cancel all pending CI runs (#8988) Lianmin Zheng 2025-08-08 16:09:50 -07:00
• 67a7d1f699 Create cancel-all-pr-test-runs (#8986) Lianmin Zheng 2025-08-08 15:53:51 -07:00
• 92cbef59ec [bug fix] Ensure local token and global token buffers are pointing to different storage (#8785) Elfie Guo 2025-08-08 15:13:32 -07:00
• b3359dc9bf Update qwen3_coder_detector.py for streaming (#8371) maocheng23 2025-08-08 14:51:03 -07:00
• 7b7e56150e [router] fix radix tree integration issues in PD router (#8982) Simo Lin 2025-08-08 14:47:51 -07:00
• 1a8706c8b9 [router] reduce contention, fix double-count race (#8978) Simo Lin 2025-08-08 14:29:14 -07:00
• 7d3af603e7 chore(ci): update Python version from 3.9 to 3.10 in sgl-kernel workflow (#8981) ishandhanani 2025-08-08 14:03:17 -07:00
• 4e7f025219 chore(gb200): update to CUDA 12.9 and improve build process (#8772) ishandhanani 2025-08-08 13:42:47 -07:00
• 36bfddecb9 [router] add metrics for worker and policy (#8971) Tony Lu 2025-08-09 04:41:40 +08:00
• 91e2f902db Fix kimi k2 function call format (#8968) Lianmin Zheng 2025-08-08 13:25:14 -07:00
• a59cbea92d [router] harden retries + metrics; fix streaming load; header filtering (#8972) Simo Lin 2025-08-08 13:10:14 -07:00
• 53f7874ae6 refine aiter_backend for mtp (#7279) valarLip 2025-08-09 02:06:02 +08:00
• 61a4680494 [router] router circuit breaker core (#8941) Simo Lin 2025-08-08 09:20:22 -07:00
• 9020f7fc32 chore: bump v0.5.0rc0 (#8959) Yineng Zhang 2025-08-08 09:16:18 -07:00
• dd650e0e21 [RL] fix skip_server_warmup and rl health_generate logic (#8757) Zilin Zhu 2025-08-08 19:34:38 +08:00
• a947154286 Revert "Support Multi Process Tokenizer Manager" (#8960) Lianmin Zheng 2025-08-08 02:28:27 -07:00
• 41357e511b chore: update flashinfer (#8958) Yineng Zhang 2025-08-08 02:15:22 -07:00
• e2fd2b9c7e Simple prefetch policy (#8692) pansicheng 2025-08-08 17:09:28 +08:00
• 7490e3f67d Support Multi Process Tokenizer Manager (#6555) ybyang 2025-08-08 16:45:50 +08:00
• 6ee6619b7a add zai-org/GLM-4.5-Air-FP8 model into nightly CI (#8894) Minglei Zhu 2025-08-08 01:44:19 -07:00
• 54ea57f245 chore: bump sgl-kernel v0.3.3 (#8957) Yineng Zhang 2025-08-08 01:35:37 -07:00
• b4c9f38a76 [NVIDIA] Fix missing get_col_major_tma_aligned_tensor for Blackwell deepgemm in EpMoE (#8955) Kaixi Hou 2025-08-08 01:12:33 -07:00
• 1132547496 Add ernie4.py for ERNIE-4.5 (#7657) Wenbo Yang 2025-08-08 15:55:48 +08:00
• 1d24db8348 Expert Parallelism for GPT-OSS (#8944) Cheng Wan 2025-08-08 00:46:42 -07:00
• 444013585d Fix typos and unify size(s)/stride(s) API calls (#8799) triple-mu 2025-08-08 15:18:08 +08:00
• 9c7e392465 bench: add attention sink op benchmark, triton and trtllm-gen [B200] (#8932) eigen 2025-08-08 03:16:23 -04:00
• 08fab2b0c4 minor: global workspace buffer for trtllm-gen mha from flashinfer (#8952) eigen 2025-08-08 03:12:12 -04:00
• 0d1e27a0c5 Better optimization log for gpt-oss model (#8953) Xiaoyu Zhang 2025-08-08 15:11:48 +08:00
• 774b47f3f1 Reduce scheduler recv requests overhead (#8947) fzyzcjy 2025-08-08 15:10:05 +08:00
• 76915d68a8 Fix enable flashinfer mxfp4 moe bf16 check (#8950) Xiaoyu Zhang 2025-08-08 13:52:09 +08:00
• 39fd178831 refactor: Move scalar_types.py to sgl-kernel to avoid circular import (#8720) Hongbo Xu 2025-08-08 10:22:16 +08:00
• ed0a3dd54a Enhancements for bench_one_batch (#8703) Zaili Wang 2025-08-08 10:00:31 +08:00
• 2e901e892f [router] dedicated prefill HTTP client and request-path optimizations (#8923) Simo Lin 2025-08-07 17:31:45 -07:00
• d3be97104b correct the tp_plan logic (#8850) Stefan He 2025-08-07 16:53:34 -07:00
• 3e7ff1ab1f fix: reasoning parser when request have enable_thinking flag (#8933) Xinyuan Tong 2025-08-07 15:52:06 -07:00
• aaf0ad8cdf remove vllm fp8quant from fp8.py (#8937) Stefan He 2025-08-07 15:50:52 -07:00
• 361379b52b docs: update README (#8929) Yineng Zhang 2025-08-07 14:28:35 -07:00
• 1ac16add8b chore: support blackwell cu129 image (#8928) Yineng Zhang 2025-08-07 14:24:57 -07:00
• c3a5fb3b28 codeowner updates for modelopt related files (#8925) Zhiyu 2025-08-07 14:21:41 -07:00
• 4bf6e5a6b0 fix: use openai 1.99.1 (#8927) Yineng Zhang 2025-08-07 14:20:35 -07:00
• 3ae33fcd0a Fix hopper launch gpt-oss model illegal memory (#8908) Xiaoyu Zhang 2025-08-08 01:02:40 +08:00
• 500b15c960 [router] upgrade router version to 0.1.9 (#8844) Simo Lin 2025-08-07 09:29:12 -07:00
• 16a4c66d25 [router] update pd router ci summary step with new threshold (#8916) Simo Lin 2025-08-07 07:15:38 -07:00
• 89e6521c61 [router] re-enable pd router benchmark CI (#8912) Simo Lin 2025-08-07 06:29:36 -07:00
• fd05b56750 refactor(sgl-router): Replace once_cell with LazyLock in worker.rs and remove once_cell dependency from Cargo.toml (#8698) Tien Nguyen 2025-08-07 20:14:03 +07:00
• 482c3db29f Fix sgl-kernel arch and missing package in CI (#8869) fzyzcjy 2025-08-07 17:08:15 +08:00
• 47824c1488 [Perf] Auto enable best flashinfer mxfp4 kernel in b200 (#8898) Xiaoyu Zhang 2025-08-07 16:08:41 +08:00
• c36a6693f3 Disable gemma3 for SWA due to CUDA illegal memory access error (#8895) Xinyuan Tong 2025-08-07 00:44:44 -07:00
• 62f8eb48b1 [CPU] Fix fallback allgather issue (#8041) blzheng 2025-08-07 15:08:18 +08:00
• b7cd743038 [Feat] QWen-1M context support[2/2]: Update block sparse attention backend (#5949) PGFLMG 2025-08-07 14:49:36 +08:00