Commit Graph

Select branches

Hide Pull Requests

bot/update-est-time-20260928

dsv41-pd

dsv41-pd-visioncp

main

Mono Color

• a416af4be7 Fix capture_sizes range for pcg (#17956) Cheng Wan 2026-01-29 12:46:35 -08:00
• 1b6798a6a4 Fix torch.__version__ for PEP440 (#15682) EduardDurech 2026-01-29 20:55:13 +01:00
• 4f2b73baf6 [MUSA] Add labeler config (#17923) R0CKSTAR 2026-01-30 01:58:54 +08:00
• d417c6809e Add tool call tests for DeepSeek V3.2 in nightly CI (#17951) Hudson Xing 2026-01-30 01:50:54 +08:00
• 88fb927cc9 [diffusion]: add dummy device attribute to fix AttributeError (#17949) Ratish P 2026-01-29 23:05:12 +05:30
• 0769de9b0f Support LightOnOCR-2-1B (#17806) Shivam jindal 2026-01-29 20:33:41 +05:30
• 3c9cc44ff5 Add mxfp8 support for online quantization, Triton dense linear, and CUTLASS MoE (#17449) Ziang Li 2026-01-29 05:33:57 -08:00
• cfa09d311c [NPU] add support for npu x86_64 image release (#14127) 22dimensions 2026-01-29 21:23:56 +08:00
• 3c2f4c7bbe [diffusion] model: sync with upstream z-Image (#17822) Yuhao Yang 2026-01-29 21:10:11 +08:00
• 30adf78f82 [diffusion]: align sglang diffusion AMD pyproject_other.toml diffusion dependency with pyproject.toml (#16225) RoyWangandroywang 2026-01-29 17:50:57 +08:00
• ef1c512754 Add aiter bias moe support in gpt-oss mxfp4 model (#17735) kkandwunhuang 2026-01-29 17:50:11 +08:00
• 319f6886fe [diffusion] model: move tp_rmsnorm check to WanTransformerBlock (#17792) triple-mu 2026-01-29 17:39:00 +09:00
• cdedbf1486 [diffusion] fix: resolve library mismatch in scheduler and update dit offload method name (#17916) Zhang Yiyang (SII) 2026-01-29 15:54:36 +08:00
• 7b79326751 [NPU] support GPTQ quantization on npu (#15203) 22dimensions 2026-01-29 15:48:18 +08:00
• cbf90d70ff [PD] Support KV transfer with MORI-IO (#14626) Niko Maandcwortman-amd 2026-01-29 15:22:41 +08:00
• d3cdee0a04 [MUSA][4/N] Add common device utilities, distributed backend, and custom op wiring (#17246) R0CKSTAR 2026-01-29 15:13:24 +08:00
• 9409c43593 Fix flaky tool calls in the Kimi K2.5 model (#17914) Xinyuan Tong 2026-01-28 23:58:16 -05:00
• 3c34d2c3eb [FIX] kimi_k2 reasoning parser (#17901) Xinyuan Tong 2026-01-28 22:47:09 -05:00
• 1b22f2ee1c update ascend docs (#17741) amote-i 2026-01-29 11:43:48 +08:00
• 0ff0d181ca feat: add custom request header logging (#17786) Joe Redmond 2026-01-28 19:33:08 -08:00
• f1384f5293 Integration mori backend for EP a2a data communication (#17012) 4 people 2026-01-29 11:07:34 +08:00
• 673dc09d9b [Fix][trtllm-mha] Canonicalize the strides when num_head = 1 (#17732) Jerry Ji 2026-01-28 18:11:18 -08:00
• ac16d4450e [smg][mesh] extract mesh to mesh crate to reduce compile time (#17907) Simo Lin 2026-01-29 10:58:42 +09:00
• 0368ddf9ea [JIT Kernel]Support fused_add_rmsnorm in JIT Kernel (#17677) Qi Yuhang 2026-01-29 09:29:59 +08:00
• 09a9147f59 [diffusion] model: support MOVA (#17704) 6 people 2026-01-29 09:12:08 +08:00
• 3fcda00e8c [CI] Fix CI timeouts by upgrading runai_model_streamer (related to #16937) (#17636) Prozac614 2026-01-29 09:09:45 +08:00
• d4180815a4 Make the functions in logits_processor.py and sampler.py more modular (#17885) Lianmin Zheng 2026-01-28 16:24:23 -08:00
• 0998de088b [Perf] Tune Llama-4-Scout-17B-16E-Instruct fused moe kernel (#17891) jackey hua 2026-01-28 17:06:46 -05:00
• e9d727cb92 [MUSA][7/N] Enhance CUDA / PyNccl wrapper to support MTLink connectivity detection (#17499) gingerXueandjingzhi.xue 2026-01-29 03:36:30 +08:00
• b77b0ffd60 [NPU] NZ for non-quantized MOE, Qwen3 MOE double memory consumption fix (#15904) Артем Савкинandgemini-code-assist[bot] 2026-01-28 19:55:08 +03:00
• 1953efb60e [AMD] ROCm: route W4A16 MoE to Triton and fix packed-weight loading (#17863) Jinn 2026-01-28 10:20:23 -06:00
• 1d1e72e516 [diffusion] fix: fix comfyui import typo (#17834) triple-mu 2026-01-29 00:49:55 +09:00
• f8636fbb25 [AMD] Add Kimi-K2, DeepSeek-V3.2 tests to nightly CI (#17523) MichaelandYC Tseng 2026-01-28 00:55:46 -08:00
• 6077de1237 [CI] [NPU] npu ci use existing modelscope model (#17868) Even Zhou 2026-01-28 16:51:41 +08:00
• c08b54a575 [JIT kernel] Update jit_kernel cache and develop doc (#17842) Xiaoyu Zhang 2026-01-28 15:09:47 +08:00
• 2573a262af [diffusion] doc: fix wrong docker run command (#17856) Mick 2026-01-28 14:52:33 +08:00
• 6f009961bb [model-gateway] Optimize HashRing construction to reduce heap allocations (#17575) Praneth Paruchuri 2026-01-28 12:16:40 +05:30
• 897c35b457 [model-gateway] Optimize consistent hashing hot path to eliminate allocations (#17467) Praneth Paruchuri 2026-01-28 12:16:11 +05:30
• c0b4dd68a2 Add a performance dashboard server and frontend for nightly CUDA tests (#17725) Kangyan-Zhou 2026-01-27 22:22:33 -08:00
• fb74e43707 [Diffusion] Delete sgl-kernel outdated time_embedding kernel (#17278) Xiaoyu Zhang 2026-01-28 14:18:53 +08:00
• 67fb492c9a [CI] Fix test_moe_fused_gate error (#17844) Xiaoyu Zhang 2026-01-28 12:03:17 +08:00
• a8dda2aa57 [DSv32] Overlap indexer qk projection and activation quant (#17688) Ziang Li 2026-01-27 19:46:49 -08:00
• 52bca42870 [AMD] CI - enable deepseekv3.2 on MI325-8gpu and merge perf/accuracy test suites into stage-b suites (#17633) YC TsengandBingxu Chen 2026-01-28 10:54:36 +08:00
• 1c4616a034 fix: add bias when enable mm fallback variant (#17690) Yisheng Gong 2026-01-27 17:50:49 -08:00
• 647428d8d6 [diffusion] perf: apply mul add fusion for Qwen-Image (#16299) 陈一涵andgemini-code-assist[bot] 2026-01-28 09:40:13 +08:00
• 32ea7bcdd8 [diffusion] endpoint: fix vertex generate (#17611) Yashika Gandhi - Google 2026-01-27 17:38:56 -08:00
• 88fcd8535f [diffusion] feat: add an arg for controlling the number of prefetched layers in layerwise-offload (#17693) Mick 2026-01-28 09:34:27 +08:00
• 1507dc6cdf [diffusion] fix: fix suppressing error log on non-main ranks (#17712) Mick 2026-01-28 09:29:19 +08:00
• 331a22427c [Diffusion] glm-image apply flashinfer rope (#17689) Xiaoyu Zhang 2026-01-28 08:51:37 +08:00
• 93423ff780 [AMD] Deprecate ROCm 6.3 artifacts and standardize gfx942 on ROCm 7 (#17785) Hubert Lu 2026-01-27 15:58:49 -08:00
• 8278ef0e68 Pass GPU ids to kill specified devices in script. (#17840) Liangsheng Yinandgemini-code-assist[bot] 2026-01-27 13:52:55 -08:00
• 4d00bd17a3 use shared memory for multimodal feature transport between Tokenizer and Scheduler (#16402) siyuandYuhao Yang 2026-01-28 03:01:08 +08:00
• d90c0837e5 [hybrid-model] clean up and consolidate redundant fields in RadixLinearAttention (#17660) Minglei Zhu 2026-01-27 10:37:58 -08:00
• 8acd4d7d7e Make flashMLA work on: Cu13, B300 (#17600) Yi Zhong 2026-01-27 11:12:47 -05:00
• 547e2d037e [diffusion] refactor: add arg to control the precision of dit (#17751) fsygd 2026-01-27 23:01:23 +08:00
• 1d942e4eef [DeepSeek] Update tests and document for DeepSeek V3.2 NVFP4 checkpoint (#17657) Baizhou Zhang 2026-01-27 22:10:57 +08:00
• d578b41bad [NPU] Adapt cann 8.5: use sfa and lightning indexer op from cann and CI update (#17615) monkeyLovedingandKelon 2026-01-27 19:03:53 +08:00
• 832c756549 [Doc] Tiny update description on torch compile (#17819) Baizhou Zhang 2026-01-27 18:59:04 +08:00
• c56d19b977 fix(quantization): add sgl_kernel fallback for FP4 quantize on Blackwell GPUs (#17816) MikkoParkkola 2026-01-27 11:43:17 +01:00
• dba264ac73 [PP] fix wrong weight logic for tie_word_embeddings model (#15890) Xuchun Shang 2026-01-27 17:41:17 +08:00
• 7106f6c8e1 [GLM-OCR] Support GLM-OCR Model (#17582) 3 people 2026-01-27 14:24:00 +08:00
• 81c0f5c5ad [Model] Add support for EXAONE-4.0 Model (#8205) Taemin JungandXinyuan Tong 2026-01-27 15:08:24 +09:00
• 6c9b054ab7 [Bug Fix] Fix reasoning parser when continue_final_message=true (#17065) laixinandXinyuan Tong 2026-01-27 14:04:44 +08:00
• df42f4d386 [AMD] Update dsv3.2 AMD GPU docs and unify ROCm TileLang build (#17783) Hubert Luandwufann 2026-01-26 21:10:32 -08:00
• a723d1c5ef [model-gateway] ignore error for embeddings/classify in PD router (#15931) shuwenn 2026-01-27 11:49:14 +08:00
• 57e432d951 fix: preserve disconnect events in api key middleware (#17253) shuwenn 2026-01-27 11:48:24 +08:00
• fd3b179ffd [HiCache][HA 1/N] Support HiCache storage runtime attach/detach (#15892) shuwenn 2026-01-27 11:33:19 +08:00
• 1b56a886bb [chore]: improve time tracing of model loading process (#15426) 3 people 2026-01-26 19:04:25 -08:00
• 3ad3268e06 [CI] Skip PD hybrid attention test with different TP temporarily (#17791) Shangming Cai 2026-01-27 10:59:33 +08:00
• 479ab7a4e7 model: support Kimi-K2.5 (#17789) Yuhao YangandMick 2026-01-27 10:57:00 +08:00
• 0519b0935f [diffusion] comfyui: support Qwen-Image, Multi-GPU Z-Image, and Enhanced ComfyUI Integration (#17678) 3 people 2026-01-27 10:06:42 +08:00
• 2d8c22a15e [bugfix] Internal processing of hf3fs crash # 16614 (#16938) FlyPanda 2026-01-27 10:01:50 +08:00
• 539924037f fix(processor): support InternS1 text_config in InternVL processor (#17040) Mahdi-CVandgemini-code-assist[bot] 2026-01-26 13:02:54 -08:00
• dd97e1fe38 [Docs] Add RL documentation (#17663) zijiexiaandJD 2026-01-26 12:16:54 -08:00
• 5ab76ff220 Special logic for healthcheck (#17734) ybyangandLiangsheng Yin 2026-01-27 02:26:40 +08:00
• 85d077f44d Introduce global alloc_len_per_decode & clean check decode memory (#15115) Liangsheng Yin 2026-01-26 10:26:20 -08:00
• 8643fb2f52 fix: remove truncation for test and job names in ci failure monitor (#17765) Douglas Yang 2026-01-26 09:46:33 -08:00
• bba6e38ff8 [NPU] Split pyproject npu from pyproject other (#17641) Makcum888e 2026-01-26 20:45:44 +03:00
• 51d139b867 fix: move nightly whl to cuda version folder (#17762) Douglas Yang 2026-01-26 08:13:46 -08:00
• 7bb41989fa [1/N] Optimize All Reduce - Benchmark different AR operations (#13797) Yuan Luoandluoyuan.luo 2026-01-26 22:44:13 +08:00
• 6c0f9b4824 Add test_gpt_oss_4gpu.py to B200 test suite (#17743) Alison Shao 2026-01-26 05:57:06 -08:00
• b56366f827 [NPU]DeepSeek-V3.2 support npu mlaprolog (#15381) 3 people 2026-01-26 20:42:37 +08:00
• 738b1ac988 [AMD CI] Add moonshotai/Kimi-K2-Instruct-0905 testcases (#17656) sogalin 2026-01-26 18:12:34 +08:00
• 5844cb2fd8 refactor mamba radix cache logic in server_args (#17645) Yi Zhang 2026-01-26 17:02:49 +08:00
• f6f1b6d000 Bump FI version (#17700) shaharmor98andb8zhong 2026-01-26 10:50:06 +02:00
• 2734b23481 accuracy enhancement for baichuan2-13B for npu (#16868) McZyWuandcy 2026-01-26 16:14:35 +08:00
• 6756cf18c6 remove multimodal as this is completely dead code (#17750) Simo Lin 2026-01-26 03:07:40 -05:00
• 12f794e516 [diffusion] fix: fix missing backend argument in pipelines_core initialization (#17343) Prozac614 2026-01-26 15:47:10 +08:00
• d4adff31aa update wasm endpoint (#17748) Simo Lin 2026-01-26 02:43:29 -05:00
• 48f4340b14 Exclude some diffusion package for ARM in docker release (#17745) Kangyan-Zhou 2026-01-25 23:32:39 -08:00
• ed75136e85 remove self managed wasm as it has been replaced with official smg wa… (#17746) Simo Lin 2026-01-26 01:56:33 -05:00
• 30b3192039 Merge performance/accuracy test suites into regular stage-b suites (#17609) Alison Shao 2026-01-25 22:49:19 -08:00
• 8c2d8b51e9 [model-gateway] fix wasm example2 (#17244) Praneth Paruchuri 2026-01-26 12:15:36 +05:30
• 02c1dabf5d [model-gateway] fix wasm example3 (#17277) Praneth Paruchuri 2026-01-26 12:15:21 +05:30
• 511961870f [model-gateway] Optimize WASM cache lookups using SHA-256 (#17344) Praneth Paruchuri 2026-01-26 12:14:55 +05:30
• 1a19b3987d [Model] Add Ernie4.5 VL model support (#15679) CSWYF3634076 2026-01-26 14:36:29 +08:00
• d275d47973 [NIXL] Add custom NIXL backend selection for KVManager (#17146) zackyoray 2026-01-26 08:35:38 +02:00
• 1e8db18290 [Kimi-Linear] Remove duplicated code in kimi-linear (#17731) Yuan Luo 2026-01-26 14:20:24 +08:00
• 7890a96f97 remove self managed mcp as it has been replaced with official rmcp crate (#17740) Simo Lin 2026-01-26 01:17:06 -05:00
• 52e0f65fce Update nightly-test-nvidia.yml to remove push trigger (#17625) Kangyan-Zhou 2026-01-25 21:42:36 -08:00