 Isotr0py
|
eac3b96ec0
|
[Models] Allow converting Qwen3-VL into Reranker model (#31890)
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
|
2026-01-08 08:10:15 +00:00 |
|
|
ZyyericandJee Jee Li
|
63baa28cf5
|
[Model] Enable LoRA support for tower and connector in GLM4-V (#31652)
Signed-off-by: Zyyeric <eric1976808123@gmail.com>
Co-authored-by: Jee Jee Li <pandaleefree@gmail.com>
|
2026-01-08 15:45:53 +08:00 |
|
|
ShaanveerS
|
9572f74f15
|
[Model] Enable LoRA support for tower and connector in DotsOCR (#31825)
Signed-off-by: ShaanveerS <shaanver.singh@gmail.com>
|
2026-01-08 14:50:16 +08:00 |
|
|
Andreas Karatzas
|
c4041f37a4
|
[ROCm][LoRA] Fix MoE accuracy regression by preserving float32 router weight scaling (#31931)
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
|
2026-01-08 04:17:56 +00:00 |
|
|
|
9f6dcb71ae
|
[MoE Refactor][16/N] Apply Refactor to NVFP4 (#31692)
Signed-off-by: Robert Shaw <robshaw@redhat.com>
Signed-off-by: Robert Shaw <114415538+robertgshaw2-redhat@users.noreply.github.com>
Co-authored-by: Robert Shaw <robshaw@redhat.com>
Co-authored-by: Michael Goin <mgoin64@gmail.com>
Co-authored-by: Pavani Majety <pmajety@nvidia.com>
|
2026-01-08 03:46:27 +00:00 |
|
|
Rabi Mishra
|
25eef3dc2e
|
feat(moe): Add is_act_and_mul=False support for Triton MoE kernels (#31645)
Signed-off-by: rabi <ramishra@redhat.com>
|
2026-01-08 10:27:09 +08:00 |
|
|
Robert Shaw
|
5dcd7ef1f2
|
[MoE Refactor][15/N] Apply Refactor to Fp8 (#31415)
|
2026-01-07 19:42:33 -05:00 |
|
|
Elvir Crnčević
|
ffc0a2798b
|
Add back missing DeepEP LL params (#31911)
Signed-off-by: Elvir Crncevic <elvircrn@gmail.com>
|
2026-01-07 17:47:54 -05:00 |
|
|
Xin YangandMichael Goin
|
0ada960a20
|
[Kernel] Support bias type in grouped_topk kernel (#31781)
Signed-off-by: Xin Yang <xyangx@amazon.com>
Co-authored-by: Michael Goin <mgoin64@gmail.com>
|
2026-01-07 12:16:32 -08:00 |
|
|
roikoren755
|
bf184a6621
|
Enable quantized attention in NemotronH models (#31898)
Signed-off-by: Roi Koren <roik@nvidia.com>
|
2026-01-07 17:37:19 +00:00 |
|
|
Cyrus Leung
|
b7036c87a1
|
[Refactor] Clean up pooler modules (#31897)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
|
2026-01-08 00:07:43 +08:00 |
|
|
Kate ChengandJhao-Ting Chen
|
cc6dafaef2
|
[Perf][Kernels] Enable FlashInfer DeepGEMM swapAB on SM90 (for W8A8 Linear Op) (#29213)
Signed-off-by: Kate Cheng <yunhsuanc@nvidia.com>
Signed-off-by: Jhao-Ting Chen <jhaotingc@nvidia.com>
Co-authored-by: Jhao-Ting Chen <jhaotingc@nvidia.com>
|
2026-01-07 10:53:54 -05:00 |
|
|
Cyrus Leung
|
b665bbc2d4
|
[Chore] Migrate V0 attention utils (#31891)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
|
2026-01-07 13:44:36 +00:00 |
|
|
Jared WenandIsotr0py
|
974138751b
|
[Refactor] GLM-ASR Modeling (#31779)
Signed-off-by: JaredforReal <w13431838023@gmail.com>
Co-authored-by: Isotr0py <mozf@mail2.sysu.edu.cn>
|
2026-01-07 13:08:29 +00:00 |
|
|
Andy Liu
|
d111bc53ad
|
[Bugfix][MTP] Fix GLM4 MoE fp8 loading with MTP on (#31757)
Signed-off-by: Andy Liu <andyliu@roblox.com>
|
2026-01-07 09:18:52 +00:00 |
|
|
BlankRandWentao Ye
|
0790f07695
|
[Misc] Improve error messages for unsupported types and parameters (#30593)
Signed-off-by: BlankR <hjyblanche@gmail.com>
Co-authored-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com>
|
2026-01-07 09:00:16 +00:00 |
|
|
maang
|
1f33e38e81
|
[Model] Cleanup: Remove redundant manual definition of make_empty_intermediate_tensors in GLM-4-MoE (#31869)
Signed-off-by: maang <maang_h@163.com>
|
2026-01-07 08:18:28 +00:00 |
|
|
weiyu
|
e7596371a4
|
[Refactor][TPU] Remove torch_xla path and use tpu-inference (#30808)
Signed-off-by: Wei-Yu Lin <weiyulin@google.com>
Signed-off-by: weiyu <62784299+weiyu0824@users.noreply.github.com>
|
2026-01-07 16:07:16 +08:00 |
|
|
xuebwang-amd
|
0dd5dee9b9
|
[Bugfix][Kernel] fix bias adding in triton kernel implemented fused moe (#31676)
Signed-off-by: xuebwang-amd <xuebwang@amd.com>
|
2026-01-07 07:36:13 +00:00 |
|
|
Kevin McKayandClaude Sonnet 4.5
|
4614c5a539
|
[Bugfix][Hardware][AMD] Consolidate FP8 min/max values helper function (#31106)
Signed-off-by: c0de128 <kevin.mckay@outlook.com>
Signed-off-by: Kevin McKay <kevin@example.com>
Co-authored-by: Claude Sonnet 4.5 <noreply@anthropic.com>
|
2026-01-07 06:55:03 +00:00 |
|
|
ℍ𝕠𝕝𝕝𝕠𝕨 𝕄𝕒𝕟
|
482914849c
|
[BugFix] LoRA: Support loading base_layer of experts (#31104)
Signed-off-by: Hollow Man <hollowman@opensuse.org>
|
2026-01-07 14:49:39 +08:00 |
|
|
|
0a2c2dc3f1
|
fixed mypy warnings for files vllm/v1/attention with TEMPORARY workaround (#31465)
Signed-off-by: Zhuohao Yang <zy242@cornell.edu>
Co-authored-by: Zhuohao Yang <zy242@cornell.edu>
Co-authored-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com>
|
2026-01-07 04:08:47 +00:00 |
|
|
Ce Zhaoand赵策
|
a051525e07
|
[Model] Enable LoRA support for PaliGemma (#31656)
Signed-off-by: 赵策 <alcor@mac.mynetworksettings.com>
Signed-off-by: Alcor <alcor_zhao@outlook.com>
Co-authored-by: 赵策 <alcor@mac.mynetworksettings.com>
|
2026-01-07 10:09:32 +08:00 |
|
|
Li, Jiangandgemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
|
8becf146bd
|
[Quantization][Refactor] Move CPU GPTQ kernel into MP linear (#31801)
Signed-off-by: jiang1.li <jiang1.li@intel.com>
Signed-off-by: Li, Jiang <bigpyj64@gmail.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
|
2026-01-06 19:10:18 +00:00 |
|
|
Yakine Tahtah
|
4e67a8f616
|
[Bugfix] Fix GLM-4 MoE router logits dtype for data parallel chunking (#31055)
Signed-off-by: ReinforcedKnowledge <reinforced.knowledge@gmail.com>
|
2026-01-06 17:57:56 +00:00 |
|
|
Vadim Gimpelson
|
22dffca982
|
[PERF] Speed-up of GDN attention decode part (Qwen3-Next) (#31722)
Signed-off-by: Vadim Gimpelson <vadim.gimpelson@gmail.com>
|
2026-01-06 17:32:46 +00:00 |
|
|
Jinzhen LinandMichael Goin
|
2f4bdee61e
|
[Quantization][MoE] remove unused ep logic from moe marlin (#31571)
Signed-off-by: Jinzhen Lin <jinzhen.ljz@antgroup.com>
Co-authored-by: Michael Goin <mgoin64@gmail.com>
|
2026-01-06 09:07:19 -08:00 |
|
|
roikoren755
|
28c94770ad
|
[NemotronH] Use ReplicatedLinear for fc1_latent_proj (#31807)
Signed-off-by: Roi Koren <roik@nvidia.com>
|
2026-01-06 16:00:40 +00:00 |
|
|
Robert ShawandRobert Shaw
|
af8fd73051
|
[MoE Refactor][14/N] Clean Up FI Quant Config Smuggling (#31593)
Signed-off-by: Robert Shaw <robshaw@redhat.com>
Co-authored-by: Robert Shaw <robshaw@redhat.com>
|
2026-01-06 15:47:04 +00:00 |
|
|
wang.yuqi
|
96860af655
|
[Model] rename use_pad_token to use_sep_token (#31784)
Signed-off-by: wang.yuqi <yuqi.wang@daocloud.io>
|
2026-01-06 14:16:04 +00:00 |
|
|
Jzz1943
|
2c1a4f2488
|
[Bugfix]: avoid overriding audio/text kwargs (Qwen3-Omni) (#31790)
Signed-off-by: Zhongze Jiang <jiangzhongze.jzz@ant-intl.com>
|
2026-01-06 12:59:17 +00:00 |
|
|
kzwrime
|
bf0f3a4638
|
[Bugfix] Fix torch.compile error for DP + MoE on CPU Backend (#31650)
Signed-off-by: kunzh <zhikun.wu@outlook.com>
|
2026-01-06 12:06:20 +00:00 |
|
|
|
7101e0851f
|
[Models]: Use MMEncoderAttention for MoonViT (#31738)
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
Signed-off-by: Roger Wang <hey@rogerw.io>
Signed-off-by: h100 <h100@inferact.ai>
Co-authored-by: Roger Wang <hey@rogerw.io>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
Co-authored-by: h100 <h100@inferact.ai>
|
2026-01-06 08:00:25 +00:00 |
|
|
Cyrus Leung
|
da71d44410
|
[Doc] Show that use_audio_in_video is supported in docs (#30837)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
|
2026-01-05 23:27:19 -08:00 |
|
|
maang
|
cd1245a184
|
[Cleanup] Remove redundant decoder_layer_type assignment in Qwen2 (#31760)
Signed-off-by: maang <maang_h@163.com>
|
2026-01-05 18:09:18 -08:00 |
|
|
Wentao Ye
|
ffec815422
|
[Perf] Optimize additional fill(0) in cutlass moe, 2.9% E2E throughput improvement, 10.8% TTFT improvement (#31754)
Signed-off-by: yewentao256 <zhyanwentao@126.com>
|
2026-01-05 18:01:13 -08:00 |
|
|
|
d386ab1412
|
[Docs] Improve malformed exception caused by backslash line continuations (#31694)
Signed-off-by: maang <maang_h@163.com>
Signed-off-by: maang <55082429+maang-h@users.noreply.github.com>
Co-authored-by: Cyrus Leung <cyrus.tl.leung@gmail.com>
Co-authored-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com>
|
2026-01-05 17:51:54 -08:00 |
|
|
Michael Goin
|
9513029898
|
[Bugfix] Properly apply v_scale for mimo_v2_flash (#31175)
Signed-off-by: mgoin <mgoin64@gmail.com>
|
2026-01-05 23:20:46 +00:00 |
|
|
Robert ShawandRobert Shaw
|
f6c0009afa
|
[Bugfix] Fix Broken ModelOpt NVFP4 MoE (#31742)
Signed-off-by: Robert Shaw <robshaw@redhat.com>
Co-authored-by: Robert Shaw <robshaw@redhat.com>
|
2026-01-05 23:18:38 +00:00 |
|
|
Yongye ZhuandRobert Shaw
|
776ca1e187
|
[MoE Refactor] Aiter Experts for BF16 MoE (#31542)
Signed-off-by: Yongye Zhu <zyy1102000@gmail.com>
Co-authored-by: Robert Shaw <114415538+robertgshaw2-redhat@users.noreply.github.com>
|
2026-01-05 14:52:59 -08:00 |
|
|
amitz-nvandMichael Goin
|
ee21291825
|
[Model] Nemotron Parse 1.1 Support (#30864)
Signed-off-by: amitz-nv <203509407+amitz-nv@users.noreply.github.com>
Signed-off-by: Michael Goin <mgoin64@gmail.com>
Co-authored-by: Michael Goin <mgoin64@gmail.com>
|
2026-01-05 13:00:14 -08:00 |
|
|
Wang Kunpeng
|
5708297e4e
|
[Misc][Model][Refactor] Pass the prefix into Linear layers (#31669)
Signed-off-by: Wang Kunpeng <1289706727@qq.com>
|
2026-01-05 20:03:18 +00:00 |
|
|
RickyChen / 陳昭儒
|
c455b771fd
|
[Bugfix][CPU] Fix RotaryEmbedding fallback causing gibberish with --enforce-eager (#31643)
Signed-off-by: rickychen-infinirc <ricky.chen@infinirc.com>
|
2026-01-06 01:25:38 +08:00 |
|
|
wang.yuqiandCyrus Leung
|
911d38ed99
|
[Model] Let more models to support the score template. (#31335)
Signed-off-by: wang.yuqi <yuqi.wang@daocloud.io>
Signed-off-by: wang.yuqi <noooop@126.com>
Co-authored-by: Cyrus Leung <cyrus.tl.leung@gmail.com>
|
2026-01-05 11:54:26 +00:00 |
|
|
Qiping Pan
|
a2ad15c070
|
[Model] Enable LoRA support for BLIP2 (#31620)
Signed-off-by: Qiping Pan <panqiping@outlook.com>
|
2026-01-05 08:02:24 +00:00 |
|
|
wang.yuqi
|
8be6432bda
|
[CI Failure] Fix NomicBert max_model_len validation (#31662)
Signed-off-by: wang.yuqi <yuqi.wang@daocloud.io>
|
2026-01-05 11:06:52 +08:00 |
|
|
wangxiyuan
|
bb4337b34c
|
[Platform] Deprecate seed_everything (#31659)
Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>
|
2026-01-04 18:34:04 -08:00 |
|
|
|
268b1c55ad
|
[MoE Refactor][13/N] Convert FI to Use PFNoEP (#31533)
Signed-off-by: Robert Shaw <robshaw@redhat.com>
Signed-off-by: Robert Shaw <robertgshaw2@gmail.com>
Signed-off-by: Robert Shaw <114415538+robertgshaw2-redhat@users.noreply.github.com>
Co-authored-by: Robert Shaw <robshaw@redhat.com>
Co-authored-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com>
|
2026-01-03 12:26:36 -08:00 |
|
|
jeremyteboulandJeremy Teboul
|
97a01308e9
|
Improve HF qwen3_omni: preserve audio_sample_rate in kwargs restructuring (#29255)
Signed-off-by: Jeremy Teboul <jeremyteboul@fb.com>
Co-authored-by: Jeremy Teboul <jeremyteboul@fb.com>
|
2026-01-03 04:31:09 +00:00 |
|
|
Yongye ZhuandRobert Shaw
|
a3f2f40947
|
[MoE Refactor] Explicit construct mk for flashinfer bf16 kernel (#31504)
Signed-off-by: Yongye Zhu <zyy1102000@gmail.com>
Co-authored-by: Robert Shaw <114415538+robertgshaw2-redhat@users.noreply.github.com>
|
2026-01-02 13:54:50 -08:00 |
|