|
d9c7730877
|
[Performance] Extract kv update ops from MLA attention backends (#34627)
Signed-off-by: ElizaWszola <ewszola@redhat.com>
Signed-off-by: Luka Govedič <ProExpertProg@users.noreply.github.com>
Co-authored-by: Di Wu <dw2761@nyu.edu>
Co-authored-by: Luka Govedič <ProExpertProg@users.noreply.github.com>
|
2026-03-02 10:43:19 -05:00 |
|
|
wangxiyuan
|
510bc9e1df
|
[Misc] Cleanup useless current_platform import (#35715)
Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>
|
2026-03-02 09:36:54 +00:00 |
|
|
|
8b5014d3dd
|
[Attention] FA4 integration (#32974)
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
Signed-off-by: Lucas Wilkinson <LucasWilkinson@users.noreply.github.com>
Co-authored-by: Matthew Bonanni <mbonanni@redhat.com>
Co-authored-by: Tyler Michael Smith <tyler@neuralmagic.com>
|
2026-03-01 23:44:57 +00:00 |
|
|
zhanqiuhu
|
57a96e26c9
|
Revert "[Bugfix] Disable TRTLLM attention with KV transfer enabled (#33192)" (#34832)
Signed-off-by: Zhanqiu Hu <zh338@cornell.edu>
|
2026-03-01 22:32:37 +00:00 |
|
|
Asaf Gardin
|
bbf81f9a92
|
[Mamba1] - Kernel Level Chunk Alignment for Prefix Caching (#34798)
Signed-off-by: Josephasafg <ajgard7@gmail.com>
|
2026-03-01 20:40:23 +08:00 |
|
|
Chauncey
|
7e08c22b8c
|
[Feat] Add CUDA torch fallbacks for fp8_mqa_logits/fp8_paged_mqa_logits_torch function (#35271)
Signed-off-by: chaunceyjiang <chaunceyjiang@gmail.com>
|
2026-02-28 10:12:00 +00:00 |
|
|
Micah Williamson
|
0edf101d2b
|
[ROCm] Add stablelm Head Size 80 To Supported Head Sizes For ROCM_ATTN (#35527)
Signed-off-by: Micah Williamson <micah.williamson@amd.com>
|
2026-02-28 12:16:34 +08:00 |
|
|
Gregory Shtrasberg
|
9fa6c68fa6
|
[ROCm] Enabling encoder and encoder-decoder on ROCm and AITER unified backends (#35334)
Signed-off-by: Gregory Shtrasberg <Gregory.Shtrasberg@amd.com>
|
2026-02-27 21:32:55 +00:00 |
|
|
haosdent
|
6d4f9d3ad5
|
[Bugfix] Fix DCP + FA3 crash due to missing num_splits in _forward_with_dcp (#35082)
Signed-off-by: haosdent <haosdent@gmail.com>
|
2026-02-27 22:27:06 +08:00 |
|
|
|
9c3fe9936b
|
Flashinfer cuDNN backend for Qwen3 VL ViT attention (#34580)
Signed-off-by: Max Hu <maxhu@nvidia.com>
Signed-off-by: Max Hu <hyoung2991@gmail.com>
Co-authored-by: Max Hu <maxhu@nvidia.com>
Co-authored-by: Shang Wang <shangw@nvidia.com>
|
2026-02-27 20:20:23 +08:00 |
|
|
Andrii SkliarandAndrii
|
56a6371706
|
[Update] Use FlashInfer fast_decode_plan directly instead of replication (#34687)
Signed-off-by: Andrii <askliar@nvidia.com>
Co-authored-by: Andrii <askliar@nvidia.com>
|
2026-02-26 16:31:43 -08:00 |
|
|
ElizaWszola
|
98217b09f9
|
[Performance] Extract KV cache update op from flashinfer forward (#35422)
Signed-off-by: ElizaWszola <ewszola@redhat.com>
|
2026-02-26 21:29:01 +00:00 |
|
|
Kunshang Ji
|
8ad54a991b
|
[Platform] Add current_platform.num_compute_units interface (#35042)
Signed-off-by: Kunshang Ji <kunshang.ji@intel.com>
Signed-off-by: Kunshang Ji <jikunshang95@gmail.com>
|
2026-02-24 22:22:49 -08:00 |
|
|
Benjamin Chislett
|
9fa5b25a23
|
[Bug][DSV3.2] Always prepare metadata for DeepGEMM Sparse Attention (#35075)
Signed-off-by: Benjamin Chislett <bchislett@nvidia.com>
|
2026-02-24 14:55:22 -08:00 |
|
|
|
f5972a872f
|
[Model][Spec Decode] Nemotron-H MTP and Mamba Speculative Decoding Support (#33726)
Signed-off-by: Shahar Mor <smor@nvidia.com>
Signed-off-by: Benjamin Chislett <bchislett@nvidia.com>
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
Co-authored-by: Shahar Mor <smor@nvidia.com>
Co-authored-by: Roi Koren <roik@nvidia.com>
Co-authored-by: Lucas Wilkinson <lwilkins@redhat.com>
|
2026-02-24 09:49:56 -08:00 |
|
|
R3hankhanandLi, Jiang <jiang1.li@intel.com>
|
34ce0ffd1f
|
[CPU][Perf] Accelerate Attention head for s390x using vector intrinsics (#34434)
Signed-off-by: Rehan Khan <Rehan.Khan7@ibm.com>
Co-authored-by: Li, Jiang <jiang1.li@intel.com>
|
2026-02-24 07:25:39 -08:00 |
|
|
|
a87cc50859
|
[Attn,KV-cache] Use per-head scales in the attention selector (#34281)
Signed-off-by: Your Name <you@example.com>
Signed-off-by: Eldar Kurtic <research@neuralmagic.com>
Co-authored-by: Eldar Kurtic <research@neuralmagic.com>
Co-authored-by: Your Name <you@example.com>
|
2026-02-24 09:02:43 -05:00 |
|
|
|
2ff4e51152
|
[ROCm] AITER fused RoPE+KVCache (#33443)
Signed-off-by: Rohan138 <rohanpotdar138@gmail.com>
Signed-off-by: charlifu <charlifu@amd.com>
Signed-off-by: Rohan Potdar <66227218+Rohan138@users.noreply.github.com>
Co-authored-by: charlifu <charlifu@amd.com>
Co-authored-by: Luka Govedič <ProExpertProg@users.noreply.github.com>
Co-authored-by: Douglas Lehr <91553416+dllehr-amd@users.noreply.github.com>
|
2026-02-23 19:06:00 -08:00 |
|
|
Asaf Gardin
|
95642441d0
|
[Mamba1] - Change supports_update_block_table to True (#35054)
Signed-off-by: Josephasafg <ajgard7@gmail.com>
|
2026-02-23 19:05:57 -08:00 |
|
|
haosdent
|
a2ba6a5244
|
[Bugfix] Fix prefix caching for Mamba 'all' mode (Nemotron models) (#34874)
Signed-off-by: haosdent <haosdent@gmail.com>
|
2026-02-23 17:31:51 +01:00 |
|
|
jennyyyyzhen
|
2aab2bb543
|
[ROCM] Optimize ROCM_AITER_FA spec decode eagle performance (#34541)
Signed-off-by: jennyyyyzhen <yzhen@hmc.edu>
|
2026-02-20 20:32:05 -08:00 |
|
|
Andreas Karatzas
|
cf93c1a128
|
[ROCm][AITER] Fix aiter paged_attention_v1 decode for sliding window and head_size < 64 (#34570)
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
|
2026-02-20 20:25:07 -08:00 |
|
|
Lucas Wilkinson
|
aaefc58ee0
|
[CI] Revert PRs 34818 and 33600 (#34979)
|
2026-02-20 13:25:50 -08:00 |
|
|
Huamin LiandCyrus Leung
|
1fe462168c
|
[perf] Avoid dtype promotion sync in mamba_get_block_table_tensor (#34870)
Signed-off-by: Huamin Li <3ericli@gmail.com>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>
|
2026-02-20 06:21:56 -08:00 |
|
|
Kevin McKayandLu Fang
|
8de7c636cc
|
[Bugfix][Hardware][AMD] Fix ROCM_AITER_FA speculative decoding support (#32877)
Signed-off-by: c0de128 <kevin.mckay@outlook.com>
Co-authored-by: Lu Fang <30275821+houseroad@users.noreply.github.com>
|
2026-02-19 22:25:46 -08:00 |
|
|
Matthew Bonanni
|
7743152957
|
[Attention] Refactor check_and_update_config (#33600)
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
|
2026-02-17 17:06:54 -08:00 |
|
|
Matthew BonanniandJee Jee Li
|
dc5fa77a4e
|
[Bugfix][MTP][Sparse MLA] Allow sparse MLA with MTP to run with FULL cudagraphs (#34457)
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
Co-authored-by: Jee Jee Li <pandaleefree@gmail.com>
|
2026-02-17 14:01:27 -05:00 |
|
|
Isotr0py
|
71cd89264f
|
[MM Encoder] Add Triton ViT attention backend (#32183)
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
|
2026-02-15 06:32:47 -08:00 |
|
|
Andreas Karatzas
|
de42abb366
|
[CI] Heavy refactoring of Voxtral multimodal audio model tests (#34294)
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
|
2026-02-13 20:04:29 -08:00 |
|
|
Woosuk Kwon
|
0916e7960b
|
[GDN] Use CPU tensors to build GDN metadata (#34498)
Signed-off-by: Woosuk Kwon <woosuk@inferact.ai>
|
2026-02-13 01:24:45 -08:00 |
|
|
Mengtao (Martin) YuanandMartin Yuan
|
9ea1f598ce
|
Use paged_attention_v1 for sliding window decode in rocm_aiter_fa (#34378)
Signed-off-by: Martin Yuan <myuan@meta.com>
Co-authored-by: Martin Yuan <myuan@meta.com>
|
2026-02-12 16:14:43 -08:00 |
|
|
|
f2c47886fd
|
[Attention] Add FlashInfer Sparse MLA backend (#33451)
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
Co-authored-by: Lucas Wilkinson <lwilkins@redhat.com>
Co-authored-by: Lucas Wilkinson <LucasWilkinson@users.noreply.github.com>
|
2026-02-12 17:21:54 +00:00 |
|
|
kliuae
|
64f570ab56
|
[ROCm] [aiter] Split KV cache update for AiterFlashAttention (#33681)
Signed-off-by: kliuae <kuanfu.liu@embeddedllm.com>
|
2026-02-11 16:26:44 +00:00 |
|
|
Lucas Wilkinson
|
c7914d30f9
|
Reapply [Attention][FA3] Update FA3 to include new swizzle optimization (#34043)
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
|
2026-02-11 07:07:56 -08:00 |
|
|
Kunshang Ji
|
cb9574eb85
|
[XPU][9/N] clean up existing ipex code/doc (#34111)
Signed-off-by: Kunshang Ji <kunshang.ji@intel.com>
|
2026-02-11 00:27:15 -08:00 |
|
|
Vadim Gimpelson
|
000214c4bb
|
[BUGFIX] Fix accuracy bugs in Qwen3-Next MTP (#34077)
Signed-off-by: Vadim Gimpelson <vadim.gimpelson@gmail.com>
|
2026-02-10 10:57:11 -05:00 |
|
|
Roberto L. CastroandClaude Sonnet 4.5
|
afdce12c89
|
[Perf][Kernel] Add faster topKperRow decode kernel for DeepSeek-V3.2 sparse attention (#33680)
Signed-off-by: LopezCastroRoberto <rocastro@redhat.com>
Signed-off-by: Roberto L. Castro <38211239+LopezCastroRoberto@users.noreply.github.com>
Co-authored-by: Claude Sonnet 4.5 <noreply@anthropic.com>
|
2026-02-10 10:29:52 -05:00 |
|
|
aabbccddwasd
|
179ae7da8f
|
[Revert] Fix performance regression for GLM-4.7-GPTQ decode and MTP acceptance rate (#33771)
Signed-off-by: aabbccddwasd <aabbccddwasd@qq.com>
|
2026-02-08 08:13:24 -08:00 |
|
|
Rohan Potdar
|
de3869bb4d
|
move checks out of unified_kv_cache_update custom op (#33943)
Signed-off-by: Rohan138 <rohanpotdar138@gmail.com>
|
2026-02-07 05:30:09 -08:00 |
|
|
lukec
|
15a0b9e570
|
Fix spelling errors (#33978)
|
2026-02-06 23:58:50 -08:00 |
|
|
Andreas Karatzas
|
350ca72c04
|
[ROCm][AITER] Fix AITER import regression for explicit backend selection (#33749)
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
|
2026-02-06 15:08:16 +00:00 |
|
|
Gassan Salama
|
1363e3d6d5
|
[cpu][performance] CPU Paged Attention NEON BFMMLA BF16 Implementation (#32263)
Signed-off-by: Gassan <gassan.salama@arm.com>
|
2026-02-06 15:01:48 +08:00 |
|
|
Benjamin Chislett
|
af3162d3aa
|
[Spec Decode] Unified Parallel Drafting (#32887)
Signed-off-by: Benjamin Chislett <bchislett@nvidia.com>
|
2026-02-05 12:37:18 -05:00 |
|
|
Luka Govedič
|
e3bf79ffa0
|
Revert "[Attention][FA3] Update FA3 to include new swizzle optimization" (#33841)
|
2026-02-04 19:54:27 -08:00 |
|
|
zhanqiuhu
|
bbe0574d8e
|
[Bugfix] Disable TRTLLM attention when KV transfer is enabled (#33192)
Signed-off-by: Zhanqiu Hu <zh338@cornell.edu>
|
2026-02-05 00:49:18 +00:00 |
|
|
Taeksang Kim
|
6e98f6d8b6
|
Implement zero-copy GQA for multimodal and CPU (#33732)
Signed-off-by: Taeksang Kim <ts.kim@hyperaccel.ai>
|
2026-02-04 20:11:39 +00:00 |
|
|
Lucas Wilkinson
|
0e92298622
|
[Misc] Delay deprecation of CommonAttentionMetadata properties (#33801)
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
|
2026-02-04 08:41:57 -08:00 |
|
|
Frank Wang
|
45f8fd6f97
|
[Feature] Enable TRITON_ATTN for Batch Invariance (#33688)
Signed-off-by: frankwang28 <frank.wbb@hotmail.com>
|
2026-02-04 13:27:34 +08:00 |
|
|
Lucas Wilkinson
|
2267cb1cfd
|
[Attention][FA3] Update FA3 to include new swizzle optimization (#23465)
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
|
2026-02-03 08:08:47 -08:00 |
|
|
Kunshang Ji
|
e10604480b
|
[XPU][1/N] Deprecate ipex and switch to vllm-xpu-kernels for xpu platform (#33379)
Signed-off-by: Kunshang Ji <kunshang.ji@intel.com>
|
2026-02-02 22:46:10 -08:00 |
|