 Cyrus Leung
|
44ea85137a
|
[Model] Support nested structures for TensorSchema (#26212)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
|
2025-10-04 01:20:32 -07:00 |
|
|
Harry MellorandIsotr0py
|
d3d649efec
|
Support expert parallel in Transformers backend (#26162)
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Co-authored-by: Isotr0py <mozf@mail2.sysu.edu.cn>
|
2025-10-04 04:35:04 +00:00 |
|
|
|
ea507c3a93
|
[V1] [Hybrid] Mamba2 Automatic Prefix Caching (#25752)
Signed-off-by: Stanislaw Wozniak <stw@zurich.ibm.com>
Signed-off-by: Thomas Ortner <boh@zurich.ibm.com>
Signed-off-by: Thomas Parnell <tpa@zurich.ibm.com>
Co-authored-by: Thomas Ortner <boh@zurich.ibm.com>
Co-authored-by: Thomas Parnell <tpa@zurich.ibm.com>
|
2025-10-04 06:34:22 +02:00 |
|
|
Fadi ArafehandLi, Jiang <jiang1.li@intel.com>
|
9705fba7b7
|
[cpu][perf] Accelerate unquantized-linear for AArch64 through oneDNN/ACL and weight prepack (#25948)
Signed-off-by: Fadi Arafeh <fadi.arafeh@arm.com>
Co-authored-by: Li, Jiang <jiang1.li@intel.com>
|
2025-10-04 12:16:38 +08:00 |
|
|
Bram WastiandWentao Ye
|
2f7dbc9b42
|
Add batch invariant kernel override for FlashInfer backend [2/n] (#25769)
Signed-off-by: Bram Wasti <bwasti@meta.com>
Signed-off-by: Bram Wasti <bwasti@fb.com>
Co-authored-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com>
|
2025-10-03 19:49:30 -07:00 |
|
|
Roger Wang
|
67bc0c003e
|
[Bugfix] Fix qwen3 vl dummy data generation with overrides (#26193)
Signed-off-by: Roger Wang <hey@rogerw.io>
|
2025-10-04 01:40:20 +00:00 |
|
|
Eugene Khvedchenya
|
5a05f26603
|
Fix issue of using only the part of video frame [Nemotron Nano] (#26186)
Signed-off-by: Eugene Khvedchenia <ekhvedchenia@nvidia.com>
|
2025-10-04 00:21:00 +00:00 |
|
|
|
7ef40bb983
|
[GPTOSS][DP/EP][Marlin] Enable GPTOSS DP/EP using Marlin kernels (#25488)
Signed-off-by: Varun Sundar Rabindranath <vsundarr@redhat.com>
Co-authored-by: Varun Sundar Rabindranath <vsundarr@redhat.com>
Co-authored-by: mgoin <mgoin64@gmail.com>
|
2025-10-03 20:13:13 -04:00 |
|
|
Wentao Ye
|
c1ffcb55da
|
[Refactor] Optimize FP8 MOE Backend Choice and Log (#26044)
Signed-off-by: yewentao256 <zhyanwentao@126.com>
|
2025-10-03 15:23:42 -06:00 |
|
|
Pavani Majety
|
a26917332f
|
[Quantization/NVFP4] Speed up TRTLLM NVFP4 MOE weight loading and fix K/V scale loading for MLA Attn (#25968)
Signed-off-by: Pavani Majety <pmajety@nvidia.com>
|
2025-10-03 19:35:06 +00:00 |
|
|
Chendi.XueandRoger Wang
|
dd96465fd7
|
[BugFix][QWEN-VL]fix wrong apply_rotary_emb_torch selection introduced by #24642 (#26123)
Signed-off-by: Chendi Xue <Chendi.Xue@intel.com>
Signed-off-by: Chendi.Xue <chendi.xue@intel.com>
Co-authored-by: Roger Wang <hey@rogerw.io>
|
2025-10-03 08:52:26 -07:00 |
|
|
whx
|
cbf9221992
|
[Model] Supplement to PR 24862: Pass param prefix to LLMHead (#25805)
Signed-off-by: whx-sjtu <2952154980@qq.com>
|
2025-10-03 21:34:53 +08:00 |
|
|
Paul Pak
|
5f42fc53b6
|
[backends][short_conv] CUDA graph piecewise edits (#24215)
Signed-off-by: Paul Pak <paulpak58@gmail.com>
|
2025-10-03 12:59:48 +00:00 |
|
|
Egor
|
aa5053e3fe
|
[Doc] Fixed shape description for fused_batched_moe.py (#25668)
Signed-off-by: Egor <e.a.krivov@gmail.com>
|
2025-10-03 04:00:23 -07:00 |
|
|
Wenlong WangandHarry Mellor
|
79aa244678
|
[Multi Modal] Configurable MM Profiling (#25631)
Signed-off-by: wwl2755 <wangwenlong2755@gmail.com>
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
|
2025-10-03 03:59:10 -07:00 |
|
|
Cyrus Leung
|
f9a8084e48
|
[Model] Use merge_by_field_config for MM models (InternVL family) (#26153)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
|
2025-10-03 01:59:06 -07:00 |
|
|
Cyrus Leung
|
0ad9951c41
|
[Input] Remove unused prompt field (#26097)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
|
2025-10-03 00:23:21 -07:00 |
|
|
Varun Sundar RabindranathandVarun Sundar Rabindranath
|
8c9117181d
|
[Misc] Remove typing.List (#26150)
Signed-off-by: Varun Sundar Rabindranath <vsundarr@redhat.com>
Co-authored-by: Varun Sundar Rabindranath <vsundarr@redhat.com>
|
2025-10-03 07:00:33 +00:00 |
|
|
Harry Mellor
|
10d765482d
|
FusedMoE support for the Transformers backend (#22650)
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
|
2025-10-02 23:12:15 -07:00 |
|
|
Cyrus Leung
|
39b643dc1a
|
[Model] Use merge_by_field_config for MM models (G) (#26117)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
|
2025-10-02 22:38:29 -07:00 |
|
|
Zhewen Li
|
711f485643
|
[Bugfix] Fix import gemm_afp4wfp4 failure on AMD (#26068)
Signed-off-by: zhewenli <zhewenli@meta.com>
|
2025-10-02 22:37:25 -07:00 |
|
|
TJian
|
9c5ee91b2a
|
[ROCm] [VL] [Bugfix] Fix vit flash attn dispatcher logic for ROCm (#26104)
Signed-off-by: tjtanaa <tunjian.tan@embeddedllm.com>
|
2025-10-02 22:34:53 -07:00 |
|
|
Matthew Bonanni
|
2aaa423842
|
[Attention] Move Backend enum into registry (#25893)
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
|
2025-10-02 20:32:24 -07:00 |
|
|
Matthew Bonanni
|
13cdc02173
|
Fix MTP with deepep_low_latency (#25904)
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
|
2025-10-02 21:29:49 +00:00 |
|
|
|
502640c3f9
|
[Perf] Fix and reapply move apply w8a8 block fp8 linear to class (#25696)
Signed-off-by: ElizaWszola <ewszola@redhat.com>
Signed-off-by: ElizaWszola <elizaw.9289@gmail.com>
Signed-off-by: Luka Govedič <lgovedic@redhat.com>
Signed-off-by: Luka Govedič <ProExpertProg@users.noreply.github.com>
Co-authored-by: Luka Govedič <ProExpertProg@users.noreply.github.com>
Co-authored-by: Michael Goin <mgoin64@gmail.com>
Co-authored-by: Luka Govedič <lgovedic@redhat.com>
|
2025-10-02 19:35:13 +00:00 |
|
|
Chen Zhang
|
1e50f1be70
|
[Deepseek v3.2] Support indexer prefill chunking (#25999)
Signed-off-by: Chen Zhang <zhangch99@outlook.com>
|
2025-10-02 10:29:12 -07:00 |
|
|
vllmellm
|
5e4a8223c6
|
[Qwen][ROCm] Flash Attention Rotary Embeddings (#24642)
Signed-off-by: vllmellm <vllm.ellm@embeddedllm.com>
|
2025-10-02 08:26:08 -07:00 |
|
|
Cyrus Leung
|
cc253b73d3
|
[Model] Use merge_by_field_config for MM models (D-F) (#26076)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
|
2025-10-02 08:17:35 -07:00 |
|
|
Cyrus Leung
|
7d6fb905d9
|
[Model] Use merge_by_field_config for MM models (A-C) (#26073)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
|
2025-10-02 08:17:31 -07:00 |
|
|
Jerry Zhang
|
c31246800c
|
Support RL online quantization with torchao (#23014)
Signed-off-by: Jerry Zhang <jerryzh168@gmail.com>
|
2025-10-01 16:39:29 -07:00 |
|
|
Cyrus Leung
|
1405f0c7ba
|
[Misc] Factor out common _apply_feature_select_strategy (#26003)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
|
2025-10-01 01:31:03 -07:00 |
|
|
Wenlong Wang
|
84d57342b6
|
[BugFix][MM] Fix Nonetype error when video is cache in qwen2.5-omni-thinker (#26004)
Signed-off-by: wwl2755 <wangwenlong2755@gmail.com>
|
2025-10-01 08:03:25 +00:00 |
|
|
|
2a69ab4899
|
Update to Transformers v4.56.2 (#24638)
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>
Co-authored-by: Cyrus Leung <cyrus.tl.leung@gmail.com>
Co-authored-by: Isotr0py <mozf@mail2.sysu.edu.cn>
|
2025-09-30 22:07:07 -07:00 |
|
|
Lucas Wilkinson
|
8d7da92fd7
|
[BugFix] Fix default kv-cache-dtype default for DeepseekV3.2 (#25988)
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
|
2025-09-30 21:58:31 -07:00 |
|
|
Roger Wang
|
66bca9b8bd
|
[MM] Add text-only mode for Qwen3-VL (#26000)
|
2025-09-30 21:13:42 -07:00 |
|
|
Wentao Ye
|
1244948885
|
[Log] Optimize Log for FP8MOE (#25709)
Signed-off-by: yewentao256 <zhyanwentao@126.com>
|
2025-09-30 19:18:43 -07:00 |
|
|
Harry MellorandIsotr0py
|
a388252ac4
|
Add explicit pooling classes for the Transformers backend (#25322)
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
Co-authored-by: Isotr0py <mozf@mail2.sysu.edu.cn>
|
2025-09-30 23:07:06 +01:00 |
|
|
cjackal
|
43b752c325
|
[Llama4] [multimodal] Fix misplaced dtype cast of cos_sin_cache in Llama4VisionRotaryEmbedding (#25889)
Signed-off-by: cjackal <44624812+cjackal@users.noreply.github.com>
|
2025-09-30 20:35:15 +00:00 |
|
|
Wentao Ye
|
e6a226efba
|
[Bug] Fix AttributeError: 'QKVParallelLinear' object has no attribute 'orig_dtype' (#25958)
Signed-off-by: yewentao256 <zhyanwentao@126.com>
|
2025-09-30 11:13:03 -07:00 |
|
|
Cyrus Leung
|
9f1c4ecaf2
|
[Bugfix] Token type and position embeddings fail to be applied to inputs_embeds (#25922)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
|
2025-10-01 00:23:12 +08:00 |
|
|
Pavani Majety
|
ef283548f7
|
[Bugfix] Fix accuracy issue of TRTLLM FP8 MOE and improve logging (#25895)
Signed-off-by: Pavani Majety <pmajety@nvidia.com>
|
2025-09-30 10:51:31 -04:00 |
|
|
Anion
|
f4db5e6de1
|
[Bugfix][Model] Fix inference for Hunyuan dense models (#25354)
Signed-off-by: anion <1005128408@qq.com>
Signed-off-by: Anion <123177548+Anionex@users.noreply.github.com>
|
2025-09-30 14:38:07 +00:00 |
|
|
Asaf Joseph Gardin
|
35fe398c7c
|
[Kernel][Moe Configs] Add more tuned triton configs for ExpertsInt8 and FP8 (#25858)
Signed-off-by: asafg <39553475+Josephasafg@users.noreply.github.com>
|
2025-09-30 07:30:44 -07:00 |
|
|
Cyrus Leung
|
d7e34b4210
|
[Model] Move vision_feature_select_strategy into resolve_visual_encoder_outputs (#25938)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
|
2025-09-30 11:24:57 +00:00 |
|
|
CSWYF3634076
|
ef6e0e7132
|
[Bugfix][Model]fix ernie45 moe gate&bias dtype to float32 (#25936)
Signed-off-by: wangyafeng <wangyafeng@baidu.com>
|
2025-09-30 19:11:21 +08:00 |
|
|
+6
|
fa7e254a7f
|
[New Model] DeepSeek-V3.2 (Rebased to Main) (#25896)
Signed-off-by: Chen Zhang <zhangch99@outlook.com>
Signed-off-by: youkaichao <youkaichao@gmail.com>
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
Signed-off-by: mgoin <mgoin64@gmail.com>
Signed-off-by: NickLucche <nlucches@redhat.com>
Signed-off-by: Yongye Zhu <zyy1102000@gmail.com>
Signed-off-by: Barry Kang <43644113+Barry-Delaney@users.noreply.github.com>
Signed-off-by: Lucia Fang <fanglu@meta.com>
Co-authored-by: Chen Zhang <zhangch99@outlook.com>
Co-authored-by: youkaichao <youkaichao@gmail.com>
Co-authored-by: Lucas Wilkinson <lwilkins@redhat.com>
Co-authored-by: Robert Shaw <114415538+robertgshaw2-redhat@users.noreply.github.com>
Co-authored-by: Lucas Wilkinson <LucasWilkinson@users.noreply.github.com>
Co-authored-by: yewentao256 <zhyanwentao@126.com>
Co-authored-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com>
Co-authored-by: mgoin <mgoin64@gmail.com>
Co-authored-by: Lucia Fang <116399278+luccafong@users.noreply.github.com>
Co-authored-by: Lucia Fang <fanglu@meta.com>
Co-authored-by: NickLucche <nlucches@redhat.com>
Co-authored-by: Siyuan Fu <siyuanf@nvidia.com>
Co-authored-by: Matthew Bonanni <mbonanni@redhat.com>
Co-authored-by: Xiaozhu Meng <mxz297@gmail.com>
Co-authored-by: Barry Kang <43644113+Barry-Delaney@users.noreply.github.com>
|
2025-09-30 17:14:41 +08:00 |
|
|
Zhou Jiahao
|
2e1b8bc2b6
|
[Model][Bugfix] Fix MiDashengLM audio encoder mask by removing incorrect logical_not (#25925)
Signed-off-by: zhoukz <me@zhoukz.com>
|
2025-09-30 08:15:23 +00:00 |
|
|
Harry Mellor
|
61aedb5ffe
|
MoveVllmConfig from config/__init__.py to config/vllm.py (#25271)
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
|
2025-09-29 19:49:49 -07:00 |
|
|
Wentao Yeandgemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
|
89e4050af4
|
[Bug] Fix Weight Loading for Block FP8 Cutlass SM90 (#25909)
Signed-off-by: yewentao256 <zhyanwentao@126.com>
Signed-off-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
|
2025-09-30 09:15:19 +08:00 |
|
|
Andrew Sansom
|
78a47f87ce
|
Test Prompt Embeds/LoRA compatibility and Enable LoRA Support for OPT Models (#25717)
Signed-off-by: Andrew Sansom <andrew@protopia.ai>
|
2025-09-30 08:10:58 +08:00 |
|