 Shanshan Shen
|
d626108b18
|
[ROCm][Perf] Fuse DeepSeek-V4 mHC post/pre and RMSNorm with AITER (#52737)
Signed-off-by: shen-shanshan <467638484@qq.com>
Signed-off-by: Shanshan Shen <87969357+shen-shanshan@users.noreply.github.com>
|
2026-08-20 04:51:04 +00:00 |
|
|
Summer YangandWoosuk Kwon
|
58e5ee0158
|
[refactor] consolidate cp attn ops (#52839)
Signed-off-by: Summer Yang <girasoleyang@gmail.com>
Co-authored-by: Woosuk Kwon <woosuk@inferact.ai>
|
2026-08-19 18:04:11 -07:00 |
|
|
Sage Moore
|
5bf0dbd6fd
|
[Bugfix] vLLM crashes at startup when DeepEP v2 is used with --enforce-eager wiht TRTLLM Bf16 (#51824)
|
2026-08-19 20:18:47 -04:00 |
|
|
Misha GoinandOpenAI Codex
|
541c6d64c1
|
[Bugfix][Quantization] Support CT block FP8 with Marlin (#52966)
Signed-off-by: mgoin <mgoin64@gmail.com>
Co-authored-by: OpenAI Codex <codex@openai.com>
|
2026-08-19 12:41:26 -07:00 |
|
|
Roger Wang
|
755492e37d
|
Revert "[Kernel] Gemma-4 FA4 FP8 Kernel" (#52987)
|
2026-08-19 10:48:46 -07:00 |
|
|
EgorandClaude
|
e9e1630e93
|
[Model] Support bidirectional (encoder-only) attention for DeepSeek e… (#52948)
Signed-off-by: Egor <erop001@gmail.com>
Signed-off-by: Egor <47443236+Lossfull@users.noreply.github.com>
Co-authored-by: Claude <noreply@anthropic.com>
|
2026-08-19 16:36:27 +00:00 |
|
|
|
54dd98be28
|
[CT] Support Humming for WNA16 MoE (#48918)
Signed-off-by: yiliu30 <yi4.liu@intel.com>
Co-authored-by: OpenAI Codex <codex@openai.com>
Co-authored-by: OpenAI Codex <noreply@openai.com>
Co-authored-by: Misha Goin <mgoin64@gmail.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
2026-08-19 12:31:32 -04:00 |
|
|
xuebwang-amd
|
c676232313
|
[Bugfix][Quantization] Fix OCP MX MoE emulation silently skipping mxfp6 activation QDQ (#52704)
Signed-off-by: xuebwang-amd <xuebwang@amd.com>
|
2026-08-19 11:29:29 -05:00 |
|
|
akii96
|
583a00257d
|
[ROCm] [Bugfix] Fix Triton fused shared expert alignment (#51632)
Signed-off-by: Aakif Nawaz <aakif.nawaz@amd.com>
|
2026-08-20 00:14:52 +08:00 |
|
|
Dinesh Chitlangia
|
525b7bbb3a
|
[Bugfix][CPU] Enable C++ causal_conv1d GDN path and float32 SSM cache on non-AMX AVX-512BF16 CPUs (#49688)
Signed-off-by: Dinesh Chitlangia <dineshchitlangia@gmail.com>
|
2026-08-19 10:50:59 -05:00 |
|
|
Andreas Karatzas
|
17dbd42930
|
[ROCm] Add UE8M0 scale packing for Triton silu_mul_quant (#37835)
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
|
2026-08-19 10:20:05 -05:00 |
|
|
Andreas Karatzas
|
160f7f0840
|
[ROCm][CI] Extended Fused MoE and FP8 MoE test support (#41100)
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
Signed-off-by: Andreas Karatzas <Andreas.Karatzas@amd.com>
|
2026-08-19 10:19:42 -05:00 |
|
|
Yohann PrigentandMisha Goin
|
be06873198
|
[Bugfix] compressed-tensors: restore int8 grouped WNA16 MoE support (#52002)
Signed-off-by: Yohann Prigent <prigent.yohann@gmail.com>
Co-authored-by: Misha Goin <mgoin64@gmail.com>
|
2026-08-19 07:55:59 -07:00 |
|
|
Nave Assaf
|
58de6cbdc2
|
Add NemotronH_Omni_Reasoning_V3 as a supported Nemotron architecture (#52929)
Signed-off-by: Nave Assaf <nassaf@nvidia.com>
|
2026-08-19 12:34:50 +00:00 |
|
|
hy123andOpenAI Codex
|
b160cab156
|
[Bugfix] Restore model info caching for package backends (#52690)
Signed-off-by: haoyang.qian <haoyangqian@gmail.com>
Co-authored-by: OpenAI Codex <codex@openai.com>
|
2026-08-19 11:18:10 +00:00 |
|
|
wangxiyuan
|
cba06764d7
|
[Platform] Fill in the missing backend parameter for torch.compile (#51781)
Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>
|
2026-08-19 10:31:19 +00:00 |
|
|
Woosuk Kwon
|
b09bd69b5b
|
[Model][NVIDIA] Route DSA models to the CUDA non-compiled path (#52861)
|
2026-08-19 00:13:52 -07:00 |
|
|
Nick Hill
|
ee11730751
|
[BugFix] Revert incorrect MM keep_on_cpu=True changes (#52881)
Signed-off-by: Nick Hill <nickhill123@gmail.com>
|
2026-08-19 07:07:40 +00:00 |
|
|
|
5a4c8d9924
|
[Bugfix][LoRA] Add embedding_modules for Qwen3.5 CausalLM (#48850)
Signed-off-by: m0_68169237 <m0_68169237@noreply.gitcode.com>
Co-authored-by: m0_68169237 <m0_68169237@noreply.gitcode.com>
Co-authored-by: Cursor Composer <composer@cursor.com>
Co-authored-by: Jee Jee Li <pandaleefree@gmail.com>
|
2026-08-19 04:55:20 +00:00 |
|
|
|
3130573630
|
[Model] Add GraniteSWA and GraniteMoeSWA via existing Granite (#52706)
Signed-off-by: Davis Wertheimer <davis.wertheimer@ibm.com>
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Co-authored-by: Claude <noreply@anthropic.com>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
|
2026-08-18 20:32:46 -07:00 |
|
|
Matthew Bonanniandmergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
8e46accab2
|
[Attention] Vectorize sparse MLA mask loads (#52217)
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
2026-08-18 20:32:41 -07:00 |
|
|
Nick Hill
|
deeeae75d0
|
[MM] Keep more metadata tensors on CPU (#52827)
Signed-off-by: Nick Hill <nickhill123@gmail.com>
|
2026-08-18 19:56:33 -07:00 |
|
|
Li, Jiang
|
e4d61d0d22
|
[CPU] Add AMX-only high-performance MLA backend for DeepSeek V2/V3/R1 (#52616)
Signed-off-by: jiang1.li <jiang1.li@intel.com>
|
2026-08-19 10:28:52 +08:00 |
|
|
liuzhenwei
|
b1d9337e92
|
[EPD] Allow KV consumers to omit MM embeddings (#52697)
Signed-off-by: zhenwei-intel <zhenwei.liu@intel.com>
|
2026-08-19 02:16:08 +00:00 |
|
|
Summer Yang
|
5f7a20b316
|
[nv] add pcp support in dsv3.2 (#52046)
Signed-off-by: Summer Yang <girasoleyang@gmail.com>
|
2026-08-18 14:59:08 -07:00 |
|
|
xuebwang-amdandClaude Opus 5
|
d3fafe0c27
|
[Quantization] Remove the dead ocp_mx_scheme branch from moe_kernel_quantize_input (#52603)
Signed-off-by: xuebwang-amd <xuebwang@amd.com>
Co-authored-by: Claude Opus 5 <noreply@anthropic.com>
|
2026-08-18 16:42:45 -05:00 |
|
|
Woosuk KwonandOpenAI Codex
|
01e56caaf2
|
[Bugfix][MLA] Do not use Dense MHA for GLM-5.2 (#52512)
Signed-off-by: Woosuk Kwon <woosuk@inferact.ai>
Co-authored-by: OpenAI Codex <codex@openai.com>
|
2026-08-18 11:20:48 -07:00 |
|
|
Strahinja Stamenkovicandmergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
ddbf826bee
|
[ROCm] Gate Torch FP8 scaled-MM on architecture support (#51021)
Signed-off-by: sstamenk <strahinja.stamenkovic@amd.com>
Signed-off-by: Strahinja Stamenkovic <strahinja.stamenkovic@amd.com>
Signed-off-by: Strahinja Stamenkovic <sstamenk@amd.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
2026-08-18 17:54:51 +00:00 |
|
|
Misha GoinandOpenAI Codex
|
bca7bea240
|
Remove VLLM_TEST_FORCE_FP8_MARLIN to replace with linear_backend/moe_backend (#52182)
Signed-off-by: mgoin <mgoin64@gmail.com>
Co-authored-by: OpenAI Codex <codex@openai.com>
|
2026-08-18 12:58:04 -04:00 |
|
|
fxmarty-amd
|
88b2bff2c6
|
[MOE] Standardize and abstract fused shared expert optimization selection (#51695)
Signed-off-by: Felix Marty <Felix.Marty@amd.com>
|
2026-08-18 12:56:56 -04:00 |
|
|
|
f9f066d195
|
[Bugfix][PaliGemma] Remove stale image embedding scaling (#52692)
Signed-off-by: jikuixie <jikuixie@gmail.com>
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Co-authored-by: OpenAI Codex <codex@openai.com>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
|
2026-08-18 16:00:55 +00:00 |
|
|
karthik
|
241ff8c443
|
[Model] Enable LoRA support for tower and connector in LlavaNextForConditionalGeneration (#49788)
Signed-off-by: gangula-karthik <gkarthik923@gmail.com>
|
2026-08-18 15:53:49 +00:00 |
|
|
qli88
|
e8ad2855e7
|
[Bugfix][ROCm] Fix a few int4/int8 quantization errors (#52112)
Signed-off-by: Qiang Li <qiang.li2@amd.com>
|
2026-08-18 08:31:51 +00:00 |
|
|
Jee Jee Li
|
2687fec6ef
|
Replicated embedding and norm fusion for DSV3 flat model (#48484)
Signed-off-by: Jee Jee Li <jeejeelee@inferact.ai>
|
2026-08-18 14:53:21 +08:00 |
|
|
Komal Kumar TeruandCursor
|
aa9903490c
|
[Cohere] Misc changes to cohere model definitions (#50156)
Co-authored-by: Cursor <cursoragent@cursor.com>
|
2026-08-18 04:59:57 +00:00 |
|
|
|
69d3335066
|
[Bugfix][Quantization] Guard the MXFP8 FlashInfer path on FlashInfer availability (#52648)
Signed-off-by: Han Li <han.li124@imperial.ac.uk>
Signed-off-by: Misha Goin <mgoin64@gmail.com>
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
Co-authored-by: Misha Goin <mgoin64@gmail.com>
|
2026-08-17 18:38:42 -07:00 |
|
|
kiroxu
|
cdb8545a91
|
[Kernel][Perf] Support Qwen head ratios in fused GDN MTP (#52539)
Signed-off-by: kiroxu <148877251+BabyDrangoner@users.noreply.github.com>
|
2026-08-17 18:17:40 -07:00 |
|
|
Bo Liandmergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
c296851a7d
|
[MoE] Refine FlashInfer one-sided All2All integration (#51924)
Signed-off-by: Bo Li <22713281+bobboli@users.noreply.github.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
2026-08-18 00:18:14 +00:00 |
|
|
Kunshang Ji
|
0e8989b416
|
[ROCm] gaurd on_gfx1250 call with rocm platform (#52625)
Signed-off-by: Kunshang Ji <kunshang.ji@intel.com>
|
2026-08-18 08:05:48 +08:00 |
|
|
Jakub ByczkowskiandCopilot
|
c296cf8259
|
[Bugfix] Add forward_xpu to XDRotaryEmbedding for HunyuanOCR on XPU (#52174)
Signed-off-by: Jakub Byczkowski <jakub.byczkowski@intel.com>
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
|
2026-08-18 07:54:05 +08:00 |
|
|
Canlin GuoandNick Hill
|
455edc022b
|
[ModelRunnerV2] Support prompt embeds (#42963)
Signed-off-by: gcanlin <canlinguosdu@gmail.com>
Signed-off-by: Canlin Guo <961750412@qq.com>
Signed-off-by: Nick Hill <nickhill123@gmail.com>
Co-authored-by: Nick Hill <nickhill123@gmail.com>
|
2026-08-17 21:58:50 +00:00 |
|
|
Wei Zhao
|
d1e3eee6fb
|
[Spec decode] Support Kimi-K3 DCP with DSpark (#52188)
Signed-off-by: wzhao18 <wzhao18.sz@gmail.com>
|
2026-08-17 13:08:45 -07:00 |
|
|
|
75dde08d3f
|
[Perf][MoE] Optimize deepep_v2 receiver CPU Overhead (#51114)
Signed-off-by: Lucas Wilkinson <wilkinson.lucas@gmail.com>
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
Co-authored-by: Robert Shaw <114415538+robertgshaw2-redhat@users.noreply.github.com>
|
2026-08-17 18:21:32 +00:00 |
|
|
ℍ𝕠𝕝𝕝𝕠𝕨 𝕄𝕒𝕟
|
cfbc5afbf7
|
[BugFix] lora_base_layer / routed_experts order in expert param mapping (#52552)
Signed-off-by: Hollow Man <hollowman@opensuse.org>
|
2026-08-17 17:40:51 +00:00 |
|
|
Roberto L. CastroandCodex
|
49905ad94d
|
[3/N][Feat][Perf] Add new warmup infrastructure for JITs. Add provider registry and orchestration for JIT warmup (#50174)
Signed-off-by: LopezCastroRoberto <rocastro@redhat.com>
Co-authored-by: Codex <codex@openai.com>
|
2026-08-17 10:11:14 -07:00 |
|
|
Misha Goin
|
4ab5e5012a
|
[Refactor] Simplify B12X linear kernels and warmup (#52368)
Signed-off-by: mgoin <mgoin64@gmail.com>
|
2026-08-17 09:45:45 -07:00 |
|
|
qli88
|
1d3a8b9e22
|
[ROCm][Bugfix] Fix Triton W4A16 bug in determining if transpose is required for GPTQ/AutoGPTQ (#48998)
Signed-off-by: Qiang Li <qiang.li2@amd.com>
|
2026-08-17 12:26:05 +00:00 |
|
|
|
70afdedc10
|
[K3] support recoverssm for K3 (#51855)
Signed-off-by: zjy0516 <riverclouds.zhu@qq.com>
Signed-off-by: Benjamin Chislett <bchislett@nvidia.com>
Co-authored-by: OpenAI Codex <codex@openai.com>
Co-authored-by: Benjamin Chislett <bchislett@nvidia.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
2026-08-17 19:34:14 +08:00 |
|
|
pmanczak
|
cc7cf71fc8
|
[XPU] Enable Kimi K3 KDA kernel tests on XPU (#51809)
Signed-off-by: pmanczak <pawel.manczak@intel.com>
|
2026-08-17 17:21:34 +08:00 |
|
|
pavelzak
|
7ea4b40954
|
[Hardware][NVIDIA] Add GB10 fused-MoE fp8 tuning configs (E=256, E=512) (#52502)
|
2026-08-16 20:04:15 -07:00 |
|