Commit Graph

Select branches

Hide Pull Requests

cch/megamoe-rc-v0.1

Mono Color

• 6468cb5823 [AMD] remove the redundant projection (#15178) yctseng0211 2025-12-20 14:10:46 +08:00
• e220da1723 tiny fix sampling seed for completion api (#15498) Qiaolin Yu 2025-12-19 20:32:13 -08:00
• b82c7a0ae7 [GLM-4.7] GLM-4.7 Tool Parser and Doc Update (#15333) Yuxuan Zhang 2025-12-20 12:30:44 +08:00
• c0f9b51992 [diffusion] refactor: deprecate workloadtype (#15267) Mick 2025-12-20 11:24:31 +08:00
• 5529ab5895 [model-gateway] Implement RAII load guard with response body attachment (#15507) Simo Lin 2025-12-19 17:14:52 -10:00
• 74a3349bea [ci] remove rust benchmark in unit test ci (#15510) Simo Lin 2025-12-19 16:59:41 -10:00
• b9ebf0ed63 Clean hidden_states_before_norm (#15485) Liangsheng Yin 2025-12-20 09:38:46 +08:00
• 3c116d5e5a [router] bugfix: cache_aware in grpc inbalance forward (#15473) kun-llfl 2025-12-20 08:25:46 +08:00
• 71a602883a [model-gateway] simplify workflow engine backoff and reduce duplicate reads (#15505) Simo Lin 2025-12-19 14:23:02 -10:00
• 61405b3d00 [model-gateway] Run workflow event subscribers concurrently (#15504) Simo Lin 2025-12-19 13:49:51 -10:00
• 0adfc42b99 [model-gateway] Optimize workflow engine with pre-computed dependency graph (#15503) Simo Lin 2025-12-19 13:44:57 -10:00
• ba72e759ca [model-gateway] Improve logging across core modules (#15497) Simo Lin 2025-12-19 11:35:28 -10:00
• 6afc5d497b [DSv32] Move deep_gemm.get_paged_mqa_logits_metadata to init time as metadata (#15040) YL D 2025-12-20 05:23:33 +08:00
• 2ee6c810b8 [AMD] Add TP=8 models to nightly test and make TP=2 test stable (#15296) michael-amd 2025-12-19 13:15:19 -08:00
• bd16244d93 [model-gateway] Improve logging in policies module (#15496) Simo Lin 2025-12-19 11:02:57 -10:00
• b5eb0214ca [model-gateway] Improve logging in data_connector module (#15495) Simo Lin 2025-12-19 10:57:18 -10:00
• d72e908ba5 [model-gateway] refactor: extract common graceful shutdown code before TLS branch (#15494) Simo Lin 2025-12-19 10:56:33 -10:00
• 50cad014dc [model-gateway] fix graceful shutdown for TLS/Non-TLS server (#15491) Simo Lin 2025-12-19 10:35:50 -10:00
• ef908aeb40 fixed trtllm nvfp4 backend for moe (#15022) Khush Gupta 2025-12-19 13:49:21 -05:00
• 9d0347b33a EP Support for Piecewise Cuda Graph (#14164) Yuwei An 2025-12-19 09:59:27 -08:00
• 05eb0bcc61 [diffusion] http-server: support vertex generate pathway (#15348) Yashika Gandhi - Google 2025-12-19 09:47:17 -08:00
• 5dccd9bdcc Enhance protection rules of code owners (#15406) Liangsheng Yin 2025-12-20 00:25:57 +08:00
• 933cef16cc Tiny fix mimo model conflicts with main (#15483) Liangsheng Yin 2025-12-19 23:20:59 +08:00
• 241ae17b25 [NPU] bugfix for chunkedprefill (#15166) Hexq0210 2025-12-19 22:41:17 +08:00
• 2c5a446006 [NPU]Fix for ipc handle with npu (#14138) Mayyyy 2025-12-19 22:39:04 +08:00
• f3705b0115 [diffusion] doc: add doc for attention backends (#15408) Xiaoyu Zhang 2025-12-19 22:10:29 +08:00
• 5a0ad7310e fix: update model name after weights update (#15416) shuwenn 2025-12-19 21:53:14 +08:00
• 5045aa34d3 Add MiDasheng Model Support (#15219) Jackie 2025-12-19 21:41:59 +08:00
• ff1e2ce24d [diffusion] fix: fix wrong validation on 2k resolution (#15478) Mick 2025-12-19 21:28:45 +08:00
• 1e58248808 [diffusion] multi-platform: add Sage Attention 3 Support for sm 120 (RTX5090) (#15382) ryang 2025-12-19 21:27:02 +08:00
• 46be74b4b4 [diffusion] kernel: timestep embedding kernel implementation (#12995) 66RING 2025-12-19 20:59:50 +08:00
• 1c65802648 [diffusion] feat: support multiple input images for generate mode (#15394) suyedu 2025-12-19 20:08:10 +08:00
• ba41080892 [diffusion] model: support qwen-image-edit-2511 (#15458) Yuhao Yang 2025-12-19 20:06:00 +08:00
• 89512029f1 [diffusion]Support url image input (#15262) HuangJi 2025-12-19 19:37:23 +08:00
• 92e6b3c30e [Auto Sync] Update scheduler_runtime_checker_mixin.py (20251219) (#15437) Lianmin Zheng 2025-12-19 01:46:03 -08:00
• 6559e43f30 Support FP8 MLA prefill and 128k context. (#14395) weiliang 2025-12-19 17:24:00 +08:00
• af780c59f3 [AMD] add unit-test-backend-8-gpu-amd back (#15253) yctseng0211 2025-12-19 16:59:28 +08:00
• a21aa87ec5 [AMD] Fix and add accuracy-test-2-gpu-amd back (#15415) yctseng0211 2025-12-19 16:41:14 +08:00
• fb17845723 fix: unreachable error check in retraction (#15433) shuwenn 2025-12-19 16:33:34 +08:00
• 65c098592d [sgl-kernel] chore: update deepgemm version (#13402) Fan Yin 2025-12-19 16:20:24 +08:00
• 4bf06635fc [diffusion] multi-platform: support diffusion on amd and fix encoder loading on MI325 (#13760) Yuzhen Zhou 2025-12-19 02:38:46 -05:00
• f2d64e6782 [amd] Add deterministic all-reduce kernel for AMD (ROCm) (#15340) sunxxuns 2025-12-19 02:36:03 -05:00
• 0e869f0868 [diffusion] refactor: refactor _build_req_from_sampling to use shallow_asdict (#13782) coco 2025-12-19 15:19:56 +08:00
• 173940927f Add customized sampler registration (#15423) Qiaolin Yu 2025-12-18 23:10:23 -08:00
• f228b662a7 Update readme (#15425) Lianmin Zheng 2025-12-18 23:06:00 -08:00
• a36142aa71 Fix Mindspore model import warning (#15287) b8zhong 2025-12-18 20:15:33 -08:00
• 160a06cab2 [Feature] Xiaomi MiMo-V2-Flash day0 support (#15207) Yingchun Lai 2025-12-19 11:40:07 +08:00
• a0985dd5e5 [diffusion] profiling: add bench_serving.py and VBench (#15410) Mick 2025-12-19 10:57:39 +08:00
• f6c9db4bc4 [DLLM] Fix dLLM regression (#15371) Zehuan Li 2025-12-19 10:55:46 +08:00
• e88e75a9df [Deepseek V3.2] Fix Deepseek MTP in V1 mode (#15429) b8zhong 2025-12-18 17:56:07 -08:00
• 4b4050e27e chore: update CI_PERMISSIONS (#15431) Yineng Zhang 2025-12-18 17:08:51 -08:00
• b2803ff207 [DLLM] Add CI for diffusion LLMs (#14723) Zehuan Li 2025-12-19 08:54:03 +08:00
• 9e0ef04e5b Support using different attention backend for draft decoding. (#14843) Charles Chen 2025-12-18 16:49:11 -08:00
• 216067c0cb feat(dsv32): better error handling for DeepSeek-v3.2 encoder (#14353) Jimmy 2025-12-19 08:34:27 +08:00
• e72b02db28 tiny fix lint on main (#15424) b8zhong 2025-12-18 15:55:02 -08:00
• 29e8f7f9e5 multimodal: precompute hash for MultimodalDataItem (#14354) Feng Su 2025-12-19 07:27:59 +08:00
• e0963a6cb1 [AMD] Clear pre-built AITER kernels and warmup to prevent segfaults and test timeouts (#15318) sunxxuns 2025-12-18 17:00:09 -05:00
• e0026f7c92 [Performance] optimize NSA backend metadata computation for multi-step speculative decoding (#14781) Johnsonms 2025-12-18 13:48:27 -08:00
• 9749d3e346 Update benchmarks to use HF token from environment. (#15421) Frank 2025-12-18 13:47:27 -08:00
• 2b0ddf89f5 [Tiny]Add warning for deepgemm on Blackwell (#15352) Baizhou Zhang 2025-12-18 13:45:26 -08:00
• 17e81c750a [PP] Add dynamic chunking PP test (#15395) Shangming Cai 2025-12-19 01:09:40 +08:00
• 88a405cc10 Support EPLB balancedness prometheus metric without GPU->CPU synchronize (#15401) fzyzcjy 2025-12-18 22:24:23 +08:00
• 602fe3b296 Super tiny add moe_ep_rank to prometheus labels (#15407) fzyzcjy 2025-12-18 22:23:20 +08:00
• ad9616f13a Tiny extract ModelRunnerOutput (#15400) fzyzcjy 2025-12-18 22:18:45 +08:00
• c5f4e20f2f Support GPU execution time breakdown by forward mode metrics (#15396) fzyzcjy 2025-12-18 22:18:17 +08:00
• 2c196f95a7 Tiny fix unknown route in prometheus metrics (#15404) fzyzcjy 2025-12-18 22:17:46 +08:00
• 9a7641d7bf [diffusion] profiling: include per-denoising-step timings in perf-dump-path (#15397) Xiaoyu Zhang 2025-12-18 18:43:33 +08:00
• 793c96c3d2 [perf]optimize w4afp8 kernel on deepseek-v3-0324 (#12921) Bruce-x-1997 2025-12-18 18:13:22 +08:00
• d1f0063262 Clean up __init__ function of the scheduler and event loop for PD (#15298) Lianmin Zheng 2025-12-18 01:35:14 -08:00
• 4792d1f452 [sgl-kernel][1/2] Fused qk_norm_rope for GLM4.6 (#15141) Kevin_Xiong 2025-12-18 17:07:04 +08:00
• fea2d5211d [bug fix][pp] fix inconsistent latency between tp (#15379) Xuchun Shang 2025-12-18 16:59:56 +08:00
• 56d12b4aea Fix warp illegal instruction in kimi k2 thinking PCG (#15306) Xiaoyu Zhang 2025-12-18 16:58:23 +08:00
• 374ad4cce0 Fix gpt-oss yarn with truncate argument (#14270) Liangsheng Yin 2025-12-18 16:31:15 +08:00
• 8b0a68f1bf Monkey patch deepseek-ocr's v_head_dim (#15384) Liangsheng Yin 2025-12-18 16:28:07 +08:00
• 70607e55e8 [model-gateway] Replace PolicyRegistry RwLock with DashMap for lock-free policy lookups (#15361) Simo Lin 2025-12-17 22:11:20 -10:00
• ee1ca51de8 [PP] Fix dynamic chunking strategy for PP (#15372) Shangming Cai 2025-12-18 14:24:55 +08:00
• ef7c29acd7 Fix issue: ENABLE_BELOW_SM90 cannot be enabled on aarch64 CPU (#12967) MarcoDWei 2025-12-18 13:26:42 +08:00
• 58c840db6b Split test_piecewise_cuda_graph.py to optimize CI resource usage (#15290) Alison Shao 2025-12-17 21:20:21 -08:00
• 3d42b7e7b0 unified management of environment variables for vlm cuda ipc transport (#14501) Yuhao Yang 2025-12-18 12:28:06 +08:00
• 9970ee34e8 Mistral Large 3 NVFP4 TRTLLM MoE support (#15049) elvischenv 2025-12-18 11:11:42 +08:00
• 9e7656be80 fix: adjust time for test_epd_disaggregation.py (#15354) Douglas Yang 2025-12-17 18:30:52 -08:00
• 9d4f066fb9 Add doc for qwen3 next (#15337) Yi Zhang 2025-12-18 09:53:07 +08:00
• 41683536d3 feat: DeepSeek-V3.2 Streaming tool call output (#15278) Xinyuan Tong 2025-12-18 01:43:58 +00:00
• 891ee8221f Feature/trtllm mha workspace size configurable #15089 (#15131) Dongjie Zou 2025-12-17 20:07:23 -05:00
• 8fa3dc36c5 [VLM] Support cos sin cache for Qwen3-VL & GLM-4.1V (#15205) Yuan Luo 2025-12-18 08:39:50 +08:00
• d20699a33c [Deepseek V3.2] Support Overlap Spec + NSA (#15307) b8zhong 2025-12-17 13:35:39 -08:00
• 169a75dfb8 Add request-level timestamp for when prefill finishes (#14860) Scott Lee 2025-12-17 13:34:46 -08:00
• 4128d4f5cb [CI] Migrate LoRA tests to test/registered/lora/ (#15176) Alison Shao 2025-12-17 13:19:42 -08:00
• 011d8d8970 Reserve more memory for DeepSeekOCR model and adjust server start timeout for DeepGEMM to reduce flakiness (#15277) Kangyan-Zhou 2025-12-17 13:13:05 -08:00
• 5290cef97c Fix condition check for require_gathered_buffer (#15328) Cheng Wan 2025-12-17 12:42:47 -08:00
• 726fe3e72e fix: prevent points regex from matching checkpoints/endpoints (#15120) 许霖 2025-12-18 04:38:18 +08:00
• 5d087891c9 Fix dp run error with fp8-kv enable in high concurrency test (#15241) kk 2025-12-18 03:49:18 +08:00
• 8451e22758 [DeepSeek-V32]Update nightly performance benchmark (#15308) Baizhou Zhang 2025-12-17 11:25:31 -08:00
• 53e151945a [model-gateway] optimize worker registry and reduce lock contention in grpc client fetch (#15336) Simo Lin 2025-12-17 08:49:10 -10:00
• d747147a26 [model-gateway] reduce cpu overhead (#15316) Simo Lin 2025-12-17 07:42:01 -10:00
• 0c00220795 tiny unify environ usage (#15335) Liangsheng Yin 2025-12-17 23:31:43 +08:00
• eeb2b9b259 [PP] Minor code cleanup for Pipeline Parallelism (#15329) Shangming Cai 2025-12-17 23:31:25 +08:00
• c4aed389da Super tiny rename failure_count for consistency (#15186) fzyzcjy 2025-12-17 21:21:07 +08:00
• 9d04b570bc Tiny dump native stacktraces in watchdog (#15222) fzyzcjy 2025-12-17 21:20:41 +08:00
• 3e690cce53 Add realtime token counter metrics (#15198) fzyzcjy 2025-12-17 21:20:24 +08:00