Commit Graph

Select branches

Hide Pull Requests

cch/megamoe-rc-v0.1

Mono Color

• 013a199bc6 [CI] Skip cutedsl gdn performance test in jit_kernel ci (#18783) Xiaoyu Zhang 2026-02-13 15:49:30 +08:00
• 1f39bf6523 [Bugfix] Add warnings when NSA indexer cache indice mismatch in PD module (#18727) Shangming Cai 2026-02-13 15:20:05 +08:00
• e6f7a372ef Rename request timeout env vars for waiting/running stages (#18766) Liangsheng Yin 2026-02-12 22:58:40 -08:00
• 5700b19cbf [diffusion] feat: support tp for qwen-image-edit-2511 (#18619) xiaoye 2026-02-13 13:04:29 +08:00
• d29e331491 [Spec] Move forward timeout before verify to fix Eagle v1 filter mismatch (#18760) Liangsheng Yin 2026-02-12 20:58:34 -08:00
• 7d4ae057ec [Kernel] Add JIT rotary_embedding_kernel (#17934) pansicheng 2026-02-13 12:41:25 +08:00
• 32e0286829 [diffusion] fix: fixe local model loading issue in bench_serving (#18687) Bhavneek Singh 2026-02-13 12:57:52 +09:00
• f4d80f9d42 [diffusion] feat: allows quality adjustment of generated images/videos (#17937) HuangJi 2026-02-13 11:56:20 +08:00
• 6555b2a71d [diffusion] fix: fix ci on amd (#18716) Bingxu Chen 2026-02-13 11:51:24 +08:00
• f65c885e7c Modify glm5 readme on npu (#18768) BourneSun0527 2026-02-13 11:42:40 +08:00
• bc2405e6c1 feat: support release lookup (#18450) shuwenn 2026-02-13 10:47:02 +08:00
• c56a5efbaa [Auto Sync] Update grok.py (20260213) (#18765) Lianmin Zheng 2026-02-12 18:41:41 -08:00
• d5f66fec15 Revert changes to weight_utils.py (#18759) Lianmin Zheng 2026-02-12 17:15:16 -08:00
• dd77bd4651 Fix invalid import paths in glm_image.py (#18757) Alison Shao 2026-02-12 16:44:34 -08:00
• 9815ee934c [Auto Sync] Update weight_utils.py (20260212) (#18692) Lianmin Zheng 2026-02-12 16:26:05 -08:00
• b48fe1d95e [Diffusion] [BUG] Fix missing initialization of GLM-Image text encoder config (#18704) Hao Jin 2026-02-12 16:19:22 -08:00
• f4417475b8 Build ROCm7.2 Image with latest AITER v0.1.10.post3 (#18741) HAI 2026-02-12 14:30:13 -08:00
• 2a8a48c0ca Reuse initialized transfer engine in mooncake store (#18460) Shangming Cai 2026-02-13 01:21:35 +08:00
• 0236522214 refactor: remove crate re-export aliases from lib.rs (#18737) Simo Lin 2026-02-12 09:17:24 -08:00
• e730c728d3 fix: image version in pypi pr workflow (#18735) Douglas Yang 2026-02-12 08:18:01 -08:00
• 9e9e949261 speed up sgl-kernel build (#18586) Xiaoyu Zhang 2026-02-12 23:43:22 +08:00
• 2f283d8152 refactor: consolidate gRPC client into shared crate dependency (#18730) Simo Lin 2026-02-12 06:43:24 -08:00
• 1b8f68af57 Fix B200 installation issue (#18725) Kangyan-Zhou 2026-02-12 22:06:23 +08:00
• b168723424 [BUGFIX] fix bug in handle mamba radix cache in server_args (#18723) Yi Zhang 2026-02-12 21:33:32 +08:00
• 92c5749f41 refactor: replace local proto compilation with smg-grpc-proto package (#18682) Simo Lin 2026-02-12 05:29:24 -08:00
• c59b9223e6 Add spec_accept_histogram request statistic (#18332) Scott Lee 2026-02-12 05:09:21 -08:00
• 0abe4a22c6 Fix flaky penalty tests by using higher temperature for effect comparison (#18380) Alison Shao 2026-02-12 05:08:37 -08:00
• f116b3a51b Make PR based docker and pypi workflow work for forked PR (#18720) Kangyan-Zhou 2026-02-12 21:05:17 +08:00
• f3656432c7 add tool_choice=auto nightly test case (#18302) Hudson Xing 2026-02-12 03:28:05 -08:00
• e20e6c28b9 [AMD] Fix accuracy issue when running TP4 dsv3 model with mtp (#18607) Thomas Wang 2026-02-12 17:13:16 +08:00
• d6f0ef677b [AMD] reset AMD image release time and reduce CI queue time (#18707) YC Tseng 2026-02-12 17:05:53 +08:00
• f20b1703ce [CI] Fix torchaudio/torchvision CUDA version mismatch (#18211) Alison Shao 2026-02-11 23:47:32 -08:00
• 1edc69be08 [Ascend]Support qwen3.5 (#18544) chenxu214 2026-02-12 15:22:47 +08:00
• 0305d12df2 [AMD] Enable release image build for ROCm 7.2.0 (#18698) Alan Kao 2026-02-12 15:16:54 +08:00
• feaa9e7e00 [diffusion] fix: replace TextEncoderConfig with Qwen3TextConfig for Z-Image (#18560) Vinh H. Pham 2026-02-12 13:31:23 +07:00
• c9297661b9 fix: /metrics endpoint always reports engine_type="unified" in PD disaggregation mode (#18552) JooYeon 2026-02-12 15:20:43 +09:00
• d91ce176bf Update README commands to include model-path option (#18557) Li Jinliang 2026-02-12 14:15:26 +08:00
• 4ed2548427 [Qwen3_5] Refactor Qwen3_5ForCausalLMMTP class implementation (#18538) Zheng Li 2026-02-12 13:38:26 +08:00
• 454676811e [Flashinfer Autotune] Fix FlashInfer FP4 MoE autotuning crash by removing incorrect flatten on hidden_states_scale (#18500) YAMY 2026-02-11 21:31:27 -08:00
• 20554a0a4f [AMD] rocm 7.2 image release, PR test, Nightly Test (#17799) YC Tseng 2026-02-12 13:29:25 +08:00
• 93ede0db19 Update ci permission (#18693) Ke Bao 2026-02-12 13:25:43 +08:00
• 3404dda592 Try fix the max-parallel for maunally triggered test again. (#18686) Liangsheng Yin 2026-02-11 20:08:25 -08:00
• e422bcaed8 [Mamba] Add float16 support for SSM cache dtype (#18444) danielafrimi 2026-02-12 05:27:47 +02:00
• 7e262b6496 Update modelopt quantization config parsing (#13919) Zhiyu 2026-02-11 19:08:29 -08:00
• b2d7fd5c87 fix the max-parallel for /rerun-stage (#18658) Liangsheng Yin 2026-02-11 19:06:51 -08:00
• 123f57b84b update glm5 readme on npu (#18657) fy 2026-02-12 10:37:12 +08:00
• 10c6bee74f List more CI runs for pr-test (#18650) Liangsheng Yin 2026-02-11 18:36:45 -08:00
• 41e1fd0be7 [diffusion] fix: webui cannot correctly display generated video using wan2.2 (#18473) R0CKSTAR 2026-02-12 10:35:39 +08:00
• c34832c02c glm5 md (#18655) liupeng374 2026-02-12 10:11:59 +08:00
• 165aff38e1 Add CI permission for Chen-0210 (#18494) Jincong Chen 2026-02-12 09:33:35 +08:00
• dc1309fc7e Avoid kimi linear stream sync (#16186) Yi Zhong 2026-02-11 20:27:22 -05:00
• 539bbf485c [Bugfix] fix config bug caused by PR #18273 (#18535) Jiayi Yan 2026-02-12 09:26:46 +08:00
• 2bd8363486 [PCG] GPT OSS Triton Kernel Support (#18405) Yuwei An 2026-02-11 17:23:55 -08:00
• f06ab17a73 [diffusion] docs: consolidate diffusion documentation into docs (#18095) qianyue76 2026-02-12 08:55:07 +08:00
• 7eaf866846 [CI] Install python3-dev for Triton JIT compilation on fresh runners (#18644) Alison Shao 2026-02-11 16:28:57 -08:00
• 5875ef0a34 Clean up noisy startup log messages and refactor loader.py (#18531) Lianmin Zheng 2026-02-11 16:12:57 -08:00
• ded068a76e Add LMF2 MoE model architecture (#17997) Piotr Mazurek 2026-02-11 18:03:43 +01:00
• 5d185efb78 Fix prefill stats for dllm (#18632) Ke Bao 2026-02-12 01:00:30 +08:00
• dcc63dc545 [CI] Guard python3 call in install script for fresh runners (#18609) Alison Shao 2026-02-11 08:05:29 -08:00
• 98b5013d59 add support to enable lora with embedding models (#17780) Vedant V Jhaveri 2026-02-11 07:19:40 -08:00
• 947927bdb5 [V3.2] Change default CP token split method to --round-robin-split (#18613) Baizhou Zhang 2026-02-11 20:14:35 +08:00
• 4f7422f7ba [NPU] support model skywork-reward-gemma2-2-27B-v0.2 (#16947) McZyWu 2026-02-11 15:34:53 +08:00
• 72c1526657 Register cp-atten-allgather buffers with symm memory (#17756) sky 2026-02-11 15:26:37 +08:00
• a8eef53dc4 Fp8 prefill attn kernel integration (#18528) Thomas Wang 2026-02-11 15:23:48 +08:00
• 2cc235e795 Fix Bug on dsv3.2 (#18553) BourneSun0527 2026-02-11 14:39:01 +08:00
• d84d2063d3 [AMD] Fix Janus-Pro crash and add Kimi-K2.5 nightly test (#18269) Michael 2026-02-10 22:33:13 -08:00
• cd90346a2b Add cache hit rate UT (#18566) Liangsheng Yin 2026-02-10 21:27:41 -08:00
• 50f74285e9 Tiny fix regex warning (#18592) Liangsheng Yin 2026-02-10 21:07:53 -08:00
• 8d2892330c chore: fix some typos (#18577) cutetocute 2026-02-11 12:47:41 +08:00
• a2c38f7796 Enhance SMG guide with RL rollout systems benefits (#18588) 赵晨阳 2026-02-10 20:20:45 -08:00
• 3167bcc01c [Doc] Comprehensive Guide: Navigating DP, DPA, and SMG Best Practices (#18096) AlexZhao 2026-02-11 10:31:28 +08:00
• 93fca0bbc3 Fix wrong prefill log. (#18570) Liangsheng Yin 2026-02-10 15:54:03 -08:00
• 2bfab1bb67 Fix radix cache key to include generated tokens in multi-turn (regression) (#16521) Yi-Chia Chen 2026-02-11 06:08:34 +08:00
• 4262f5259b Tilelang sparse decode fwd for dsv32 mi355 (#18488) Thomas Wang 2026-02-11 01:53:26 +08:00
• 2d38b8aca0 Revert "[sgl-kernel] upgrade deepgemm" (#18562) Baizhou Zhang 2026-02-11 01:17:40 +08:00
• 573ff55814 [NPU][docs]fix bug about hyperlink for best practice for ascend npu (#18561) husf 2026-02-11 01:03:28 +08:00
• 44603764d6 fix(config): Support setting Mamba state dtype via config file (#18532) Zheng Li 2026-02-11 00:20:06 +08:00
• d0d387dea1 [NPU] update npu doc (#18474) Hexq0210 2026-02-10 21:59:13 +08:00
• 99101ce30b [NPU][docs] improve docs for Best Practice on Ascend NPU (#18360) husf 2026-02-10 21:52:27 +08:00
• bec7fe9e65 [sgl-kernel] upgrade deepgemm (#18362) Xiaoyu Zhang 2026-02-10 21:31:30 +08:00
• efcdda0176 [diffusion] fix: fix fsdp (#18187) Mick 2026-02-10 20:22:20 +08:00
• 49cbb469b4 [NPU] [CI] Enable run multimodal NPU CI when changes only in multimodal_gen (#18523) Makcum888e 2026-02-10 14:53:43 +03:00
• 47978ee858 [diffusion] feat: support parallel wan-vae decode (#18179) wxy 2026-02-10 18:32:00 +08:00
• 26f2b3798d [DLLM] Basic dLLM scheduling strategy and implementation (#17484) Zehuan Li 2026-02-10 16:54:15 +08:00
• 8da14aea88 [HiCache] fix: StorageMetricsCollector was initialized twice (#18354) shuwenn 2026-02-10 16:53:00 +08:00
• d94d0af573 [AMD] Turn on aiter-prebuild (#18425) YC Tseng 2026-02-10 16:49:35 +08:00
• 398b81f78c Support GlmMoeDsaForCausalLM (#18521) Xinyuan Tong 2026-02-10 02:20:10 -05:00
• e8a2c13380 Deepseekv32 compatibility with transformers v5 (#18297) Xinyuan Tong 2026-02-10 01:50:40 -05:00
• 0b15f19927 [EPD] Add notification mechanism to fix server hang and add timeout env var (#18229) siyu 2026-02-10 11:52:54 +08:00
• 1d366f1206 Make bench_one_batch_server compatible for more backends (#18512) maocheng23 2026-02-09 18:36:39 -08:00
• 4a1b50bb2d Fix idle batch predict dtype in spec v2 (#18379) Qiaolin Yu 2026-02-09 18:29:13 -08:00
• df733c5ee5 [HiCache][PP] add test case for compatibility (#16395) Teng Ma 2026-02-10 10:03:04 +08:00
• 2825f5d8e0 Tiny fix wrong metric collect key name forward_prefill -> forward_extend (#18506) Liangsheng Yin 2026-02-09 16:23:41 -08:00
• 26a006e47f Add cache_config_info metric. (#17273) Kartik Ramesh 2026-02-09 18:09:09 -06:00
• 54589a2f2d docs: expand and update modelopt documentation (#18479) Zack Yu 2026-02-09 15:09:52 -08:00
• b027c5aca6 [Auto Sync] Update cache_init_params.py (20260209) (#18502) Lianmin Zheng 2026-02-09 14:49:41 -08:00
• ce95f203b0 [Auto Sync] Update logits_processor.py (20260209) (#18503) Lianmin Zheng 2026-02-09 14:33:02 -08:00
• 01e3f4682e feat(kv-events): Add medium field to KV event types for storage tier tracking (#18205) ishandhanani 2026-02-09 14:39:15 -06:00
• 316f9cbb35 [AMD] add amd ci monitor (#17476) Bingxu Chen 2026-02-10 01:04:54 +08:00
• 27c447653d model: support Qwen3.5 (#18489) Zheng Li 2026-02-10 00:27:59 +08:00