|
8cf7c4d8ad
|
[Attention Backend] add HPC-Ops Attention backend (#46020)
Signed-off-by: chengvjiang <chengvjiang@tencent.com>
Co-authored-by: chengvjiang <chengvjiang@tencent.com>
Co-authored-by: Andreas Karatzas <akaratza@amd.com>
|
2026-06-30 18:17:43 +08:00 |
|
|
Uros Markovic
|
81bcced482
|
[Bugfix][ROCm] Preserve MoE weight padding for unquantized Triton path (#46381)
Signed-off-by: Uros Markovic <umarkovi@amd.com>
|
2026-06-30 14:47:57 +08:00 |
|
|
Kunshang Ji
|
fb42e5219e
|
[Platform] Replace torch.cuda.mem_get_info with torch.accelerator.get_memory_info (#44825)
Signed-off-by: Kunshang Ji <kunshang.ji@intel.com>
Signed-off-by: Kunshang Ji <jikunshang95@gmail.com>
|
2026-06-30 14:39:52 +08:00 |
|
|
Andreas Karatzas
|
4236514098
|
[ROCm][CI][Multimodal] Use ROCm-aware FA availability check for Unlimited-OCR (#47004)
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
|
2026-06-30 14:03:13 +08:00 |
|
|
linitra24andJee Jee Li
|
b5c9e1ac33
|
[LoRA] Add language-backbone LoRA support for MiniCPM-V 4.6 (#46740)
Signed-off-by: linitra24 <Joy25810@foxmail.com>
Co-authored-by: Jee Jee Li <pandaleefree@gmail.com>
|
2026-06-30 04:19:31 +00:00 |
|
|
Summer YangandClaude
|
5b4cb69523
|
[Bugfix][MLA] Fix LSE log-base mismatch in DCP + FlashInfer MLA decode (#47079)
Signed-off-by: girasoley <girasoleyang@gmail.com>
Co-authored-by: Claude <noreply@anthropic.com>
|
2026-06-29 19:15:02 -07:00 |
|
|
Thien Tran
|
43916891b2
|
[GDN] Improve kkt kernel of CuteDSL prefill backend (#46346)
Signed-off-by: Thien Tran <gau.nernst@yahoo.com.sg>
|
2026-06-29 18:34:18 -07:00 |
|
|
Andreas KaratzasandTyler Michael Smith
|
53f7553f09
|
[ROCm][DeepEP] Stabilize high-throughput DBO for DP+EP (#46990)
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
Signed-off-by: Andreas Karatzas <Andreas.Karatzas@amd.com>
Co-authored-by: Tyler Michael Smith <tlrmchlsmth@gmail.com>
|
2026-06-29 14:28:02 -07:00 |
|
|
zhrrr
|
61ab70ec3b
|
[Model Runner V2] support mamba hybrid models align prefix cache (#42406)
Signed-off-by: zhuhaoran <zhuhaoran.zhr@alibaba-inc.com>
|
2026-06-29 14:09:16 -07:00 |
|
|
Jee Jee Li
|
7be582697b
|
[Bugfix] Fix DeepseekV2Model hidden_size (#46986)
Signed-off-by: Jee Jee Li <jeejeelee@inferact.ai>
|
2026-06-29 16:44:05 +00:00 |
|
|
Roberto L. CastroandLucas Wilkinson
|
030c9523bd
|
[Perf][1/N] Expand Triton kernel warmup coverage, DSv4 (#46634)
Signed-off-by: LopezCastroRoberto <rocastro@redhat.com>
Signed-off-by: Roberto L. Castro <38211239+LopezCastroRoberto@users.noreply.github.com>
Co-authored-by: Lucas Wilkinson <LucasWilkinson@users.noreply.github.com>
|
2026-06-29 16:40:34 +00:00 |
|
|
Wei ZhaoandJee Jee Li
|
4708292d48
|
Bump flashinfer version to 0.6.13 (#46683)
Signed-off-by: wzhao18 <wzhao18.sz@gmail.com>
Co-authored-by: Jee Jee Li <pandaleefree@gmail.com>
|
2026-06-29 09:30:57 -07:00 |
|
|
Jason LiandXin Li
|
debec6440b
|
Add MiniMax-M3 modelopt nvfp4 support (#46756)
Signed-off-by: Xin Li <xinli@nvidia.com>
Signed-off-by: jasonlizhengjian <jasonlizhengjian@gmail.com>
Co-authored-by: Xin Li <xinli@nvidia.com>
|
2026-06-29 09:29:39 -07:00 |
|
|
HDCharles
|
379acd4e4f
|
[Bugfix][Quantization] Fix W8A8 int-quantized scheme selection regression (#46860)
Signed-off-by: HDCharles <charlesdavidhernandez@gmail.com>
|
2026-06-29 15:55:42 +00:00 |
|
|
Michael GoinandClaude Opus 4.8
|
0ca39c4f1f
|
[Bugfix] Capture final-layer aux hidden state in deepseek_v2 backbone (#46973)
Signed-off-by: mgoin <mgoin64@gmail.com>
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
|
2026-06-29 10:00:31 -04:00 |
|
|
bnellnmandRobert Shaw
|
bc8481af09
|
[MoE Refactor] Standardize Humming MoE experts + utilities (#43373)
Signed-off-by: Bill Nell <bnell@redhat.com>
Co-authored-by: Robert Shaw <114415538+robertgshaw2-redhat@users.noreply.github.com>
|
2026-06-29 06:19:29 -07:00 |
|
|
Roberto L. Castro
|
eddfd4cf21
|
[Perf][2/N] Expand Triton kernel warmup coverage, Qwen (#46750)
Signed-off-by: LopezCastroRoberto <rocastro@redhat.com>
|
2026-06-29 10:10:07 +00:00 |
|
|
soaringk
|
ab132ee98b
|
Fix model info cache for package models (#46567)
Signed-off-by: soaringk <k3vin.zhang@gmail.com>
|
2026-06-29 09:17:54 +00:00 |
|
|
Alden LoboandAlden Lobo
|
e186107870
|
[Bugfix] Use native SiLU activation in CPU fused MoE (#45961)
Signed-off-by: Alden Lobo <alden.lobo@arm.com>
Co-authored-by: Alden Lobo <alden.lobo@arm.com>
|
2026-06-29 09:12:20 +00:00 |
|
|
JohnandHarry Mellor
|
0e207dac78
|
[Bugfix] Transformers backend: apply learned lm_head.bias for tied-embedding models (#46835)
Signed-off-by: John Langford <jl@hunch.net>
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
|
2026-06-29 08:59:15 +00:00 |
|
|
Harry Mellor
|
5051698e41
|
Remove unnecessary load_weights methods (#44589)
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
|
2026-06-29 01:52:23 -07:00 |
|
|
SoyaazzandIsotr0py
|
4559c43a95
|
[MM][CG] Gemma3 Encoder CUDA Graph (#43591)
Signed-off-by: JisoLya <523420504@qq.com>
Signed-off-by: Soyaazz <523420504@qq.com>
Co-authored-by: Isotr0py <mozf@mail2.sysu.edu.cn>
|
2026-06-29 04:52:00 +00:00 |
|
|
Yuwen Zhou
|
58d6a6e60a
|
[CPU] Support cpu compressed-tensor w8a8 int8 moe (#42920)
Signed-off-by: yuwenzho <yuwen.zhou@intel.com>
Signed-off-by: Yuwen Zhou <yuwen.zhou@intel.com>
|
2026-06-29 03:04:05 +00:00 |
|
|
Ilya MarkovandMarkov Ilya
|
a2abce646f
|
[EPLB] Mask padding in EPLB load recording (#38128)
Signed-off-by: ilmarkov <markovilya197@gmail.com>
Signed-off-by: Markov Ilya <markovilya19@gmail.com>
Co-authored-by: Markov Ilya <markovilya19@gmail.com>
|
2026-06-28 19:43:58 -07:00 |
|
|
Harry Mellor
|
311ad689ad
|
Remove boilerplate missed by #46820 (#46956)
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
|
2026-06-29 08:11:17 +08:00 |
|
|
|
4dfbf1503b
|
[Model] Add support for openai/privacy-filter (#41026)
Signed-off-by: Fabian Joswig <fjosw@users.noreply.github.com>
Co-authored-by: wang.yuqi <yuqi.wang@daocloud.io>
Co-authored-by: Tyler Michael Smith <tlrmchlsmth@gmail.com>
|
2026-06-28 16:18:22 -07:00 |
|
|
fxmarty-amdandAndreas Karatzas
|
03c6d01c30
|
[OCP MX ] Add back emulation to available OCP MX backends list (#46629)
Signed-off-by: Felix Marty <Felix.Marty@amd.com>
Co-authored-by: Andreas Karatzas <akaratza@amd.com>
|
2026-06-28 12:43:19 -05:00 |
|
|
Gonzague de CarpentierandHarry Mellor
|
7544286b04
|
[Bugfix] Transformers backend: recompute mm_token_type_ids per request for M-RoPE (#46552)
Signed-off-by: Gonzague de Carpentier <decarpentierg@gmail.com>
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
|
2026-06-28 15:19:28 +00:00 |
|
|
Woosuk Kwon
|
89876b0c54
|
[GLM5] Implement op fusion for GLM5/DSV3.2 (#46876)
|
2026-06-28 08:17:39 -07:00 |
|
|
Wentao Ye
|
5c91039c41
|
[GLM5.2 Perf] Replace MOE all-reduce with reduce-scatter, 3.1%~3.2 E2E Throughput improvement (#46635)
Signed-off-by: yewentao256 <zhyanwentao@126.com>
|
2026-06-28 14:55:54 +00:00 |
|
|
frida-anderssonandAndreas Karatzas
|
6eb63a1da6
|
[Bugfix][DSv3.2] Skip indexer weights for index-cache-skipped layers (#46600)
Signed-off-by: Frida Andersson <fanderss@amd.com>
Co-authored-by: Andreas Karatzas <akaratza@amd.com>
|
2026-06-28 01:37:44 -07:00 |
|
|
Shanshan ShenandIsotr0py
|
35e6c86caa
|
[Bugfix][MM][CG] Enable dual-path ViT CUDA graph for Step3-VL (#46034)
Signed-off-by: shen-shanshan <467638484@qq.com>
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
Co-authored-by: Isotr0py <mozf@mail2.sysu.edu.cn>
|
2026-06-28 00:06:43 -07:00 |
|
|
|
c7ca0bccae
|
[ROCm][Perf] Add Fused Shared Expert (FSE) support for GLM-4.5/6/7 (#44313)
Signed-off-by: Olga Miroshnichenko <olga.miroshnichenko@amd.com>
Signed-off-by: Mehdi Ghanimifard <mehdi.ghanimifard@amd.com>
Co-authored-by: Mehdi Ghanimifard <mghanimi@amd.com>
Co-authored-by: Mehdi Ghanimifard <mehdi.ghanimifard@amd.com>
|
2026-06-28 00:04:08 -07:00 |
|
|
|
c6741b2ad4
|
[Model] Support Unlimited OCR (#46564)
Signed-off-by: Tianyu Guo <guoty9@mail2.sysu.edu.cn>
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
Co-authored-by: Isotr0py <mozf@mail2.sysu.edu.cn>
Co-authored-by: Roger Wang <hey@rogerw.io>
|
2026-06-27 23:09:18 -07:00 |
|
|
jj shaoandshaojinjie.sjj
|
ea2ead1db3
|
[Misc] Fix incorrect layer type annotation in Fp8LinearMethod (#46818)
Signed-off-by: shaojinjie.sjj <shaojinjiesjj@gmail.com>
Co-authored-by: shaojinjie.sjj <shaojinjiesjj@gmail.com>
|
2026-06-27 20:23:59 +00:00 |
|
|
|
867fd5e8ed
|
[ROCm][Perf] Use flydsl moe with Minimax-M3 mxfp8 weights on gfx950 and implemented moe-backend selection (#46184)
Signed-off-by: Hongxia Yang <hongxia.yang@amd.com>
Signed-off-by: tjtanaa <tunjian.tan@embeddedllm.com>
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Co-authored-by: TJian <tunjian.tan@embeddedllm.com>
Co-authored-by: Andreas Karatzas <akaratza@amd.com>
Co-authored-by: Tan Pin Siang <tanpinsiang@gmail.com>
|
2026-06-27 10:22:57 +00:00 |
|
|
Wentao Ye
|
b588f66dc2
|
[GLM5.2 Perf] fused_indexer_q_rope_quant triton kernel, 1.9% ~ 3.3% E2E Throughput improvement. (#46862)
Signed-off-by: yewentao256 <zhyanwentao@126.com>
|
2026-06-26 22:16:20 -07:00 |
|
|
|
ddd3855a28
|
[MoE Backend] add HPC-Ops MoE backend (#45924)
Signed-off-by: chengvjiang <chengvjiang@tencent.com>
Co-authored-by: chengvjiang <chengvjiang@tencent.com>
Co-authored-by: youkaichao <youkaichao@gmail.com>
|
2026-06-27 11:18:07 +08:00 |
|
|
Nick Hill
|
c6dd32a810
|
[ModelRunner V2] Support realtime embeddings (#46762)
|
2026-06-26 19:42:27 -07:00 |
|
|
Nick Hill
|
b94f212e37
|
[ModelRunner V2] Deduplicate ModelState init logic (#46776)
Signed-off-by: Nick Hill <nickhill123@gmail.com>
|
2026-06-26 16:32:45 -07:00 |
|
|
Harry Mellor
|
d8eb734d94
|
Fix Transformers backend FP8 MoE and remove some boilerplate (#46820)
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
|
2026-06-27 00:16:05 +01:00 |
|
|
|
701a23d99f
|
[Bugfix][Model] Support tensor parallelism for DiffusionGemma (#45719) (#46177)
Signed-off-by: Carlos Alvarado <carlos-alvarado@outlook.com>
Co-authored-by: Claude <noreply@anthropic.com>
Co-authored-by: Lucas Wilkinson <LucasWilkinson@users.noreply.github.com>
|
2026-06-26 20:05:04 +00:00 |
|
|
Julien Denize
|
3d3b96488f
|
Migrate Voxtral to mistral-common 1.11.5 audio API (#46705)
Signed-off-by: Julien Denize <40604584+juliendenize@users.noreply.github.com>
|
2026-06-26 11:06:31 -07:00 |
|
|
fxmarty-amd
|
37ce34922f
|
[CI] Fix failing CUDA graph capture in Triton MOE (#46735)
Signed-off-by: Felix Marty <Felix.Marty@amd.com>
|
2026-06-26 07:21:20 -07:00 |
|
|
Hongxia YangandClaude Opus 4.8
|
c2507fb293
|
[ROCm] [MoE] [Perf] Shared-expert fusion for bias-routed MoE; enable on MiniMax-M3 mxfp8 model (#46545)
Signed-off-by: Hongxia Yang <hongxia.yang@amd.com>
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
|
2026-06-26 07:05:20 -07:00 |
|
|
TJian
|
8921c4be88
|
[ROCm] [Performance] Optimize aiter moe for DeepSeekV4 (#46122)
Signed-off-by: tjtanaa <tunjian.tan@embeddedllm.com>
|
2026-06-26 06:43:27 -07:00 |
|
|
qli88andTJian
|
8e394244a5
|
[ROCm]Enable AITER MoE backend for MiniMax-M3-MXFP4 (#46419)
Signed-off-by: Qiang Li <qiang.li2@amd.com>
Co-authored-by: TJian <tunjian.tan@embeddedllm.com>
|
2026-06-26 06:35:35 -07:00 |
|
|
Tiezhen WANG
|
c7645bce04
|
Remove grok model arch from vllm (#46706)
Signed-off-by: Xianbao QIAN <xianbao.qian@gmail.com>
|
2026-06-25 23:02:10 -07:00 |
|
|
fxmarty-amd
|
552a9dbe59
|
[NVFP4][Emulation] Fuse NVFP4 weight dequantization with compute in triton kernel for w13/w2 MOE MLP linears (#44667)
Signed-off-by: Felix Marty <Felix.Marty@amd.com>
|
2026-06-25 19:33:00 -07:00 |
|
|
Giancarlo Delfinandmergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
02a1f23711
|
[DFlash] Fuse precompute kv per-layer rmsnorms (#46761)
Signed-off-by: Giancarlo Delfin <gdelfin@inferact.ai>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
2026-06-25 19:32:07 -07:00 |
|