 Woosuk Kwon
|
287471b994
|
[Model Refactoring] Migrate DeepSeek V4 to vllm/models/ [1/N] (#43004)
Signed-off-by: Woosuk Kwon <woosuk@inferact.ai>
|
2026-05-18 19:50:02 -07:00 |
|
|
Wentao Ye
|
37ece593c1
|
[Perf] Padded nvfp4 quant kernel to remove additional copy, 2.4%~5.7% e2e performance improvement (#42774)
Signed-off-by: yewentao256 <zhyanwentao@126.com>
|
2026-05-18 16:38:12 -07:00 |
|
|
Wentao Ye
|
cd49a05d5a
|
[Refactor] Remove dead code (#42889)
Signed-off-by: yewentao256 <zhyanwentao@126.com>
|
2026-05-18 16:41:22 -04:00 |
|
|
Tuukka Sarvi
|
8fc1c284b9
|
[ROCm] Guard AITER GDN decode fast path by layout (#42880)
Signed-off-by: Tuukka Sarvi <tuukka.sarvi@amd.com>
|
2026-05-18 11:56:22 -07:00 |
|
|
Amit Portnoy
|
ce88f01c9a
|
[Docs] update attribution to reflect EDEN foundation (#41666)
Signed-off-by: amitport <1131991+amitport@users.noreply.github.com>
|
2026-05-18 11:22:56 -07:00 |
|
|
czhu-cohere
|
9758a6e5c5
|
[BugFix] support PP for Cohere vision model (#42819)
Signed-off-by: <conway.zhu@cohere.com>
Signed-off-by: root <conway.zhu@cohere.com>
|
2026-05-18 11:12:06 -07:00 |
|
|
Bowen Bao
|
a2c8fc6657
|
[ROCm][Quantization][3/N] Refactor quark_moe w4a4 w/ oracle (#41436)
Signed-off-by: Bowen Bao <bowenbao@amd.com>
|
2026-05-18 13:46:13 -04:00 |
|
|
Jinzhen LinandMichael Goin
|
6859ca7615
|
[Bugfix] fix swiglu limit issue for humming backend + deepseek v4 (#42541)
Signed-off-by: Jinzhen Lin <jinzhen.ljz@antgroup.com>
Co-authored-by: Michael Goin <mgoin64@gmail.com>
|
2026-05-18 17:32:26 +00:00 |
|
|
Mohammad Miadh Angkad
|
67f58ce23f
|
[Bugfix] Fix DSV4 MTP after ROCm mHC integration (#42930)
Signed-off-by: Mohammad Miadh Angkad <176301910+mmangkad@users.noreply.github.com>
|
2026-05-18 17:02:01 +00:00 |
|
|
Wei Zhao
|
8c296de63b
|
[Perf] Re-enable flashinfer autotune by default and cleanup (#42857)
Signed-off-by: wzhao18 <wzhao18.sz@gmail.com>
|
2026-05-18 09:12:27 -07:00 |
|
|
|
78e7a7b9b0
|
Refactor AWQ Marlin MoE onto modular WNA16 oracle (#42483)
Signed-off-by: Siddharth Bedekar <bedeksid@gmail.com>
Signed-off-by: Siddharth Bedekar <104613085+bedeks@users.noreply.github.com>
Co-authored-by: Robert Shaw <robertgshaw2-redhat@users.noreply.github.com>
Co-authored-by: OpenAI Codex <codex@openai.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
2026-05-18 08:02:43 -07:00 |
|
|
roikoren755
|
737bfa3a43
|
[Bugfix][Hybrid][NemotronH] Fix mamba_cache_mode=all + speculative decoding crash (#41233)
Signed-off-by: Roi Koren <roik@nvidia.com>
|
2026-05-18 14:54:00 +03:00 |
|
|
inisisandYongye Zhu
|
df852ed503
|
fix: remove unused norm for dpskv4 (#41710)
Signed-off-by: inisis <desmond.yao@buaa.edu.cn>
Co-authored-by: Yongye Zhu <zyy1102000@gmail.com>
|
2026-05-18 18:33:29 +08:00 |
|
|
Yuwen Zhou
|
88a860d754
|
[CPU] Add MXFP4 W4A16 MoE support (#41922)
Signed-off-by: yuwenzho <yuwen.zhou@intel.com>
Signed-off-by: Yuwen Zhou <yuwen.zhou@intel.com>
|
2026-05-18 03:04:45 -07:00 |
|
|
Li, Jiang
|
b4601ad43f
|
[CPU] Add fused GDN support for AMX CPU platform (#42707)
Signed-off-by: jiang1.li <jiang1.li@intel.com>
|
2026-05-18 03:04:36 -07:00 |
|
|
Jee Jee Li
|
2267f70070
|
[Kernel] Pack topk id/weights triton kernel (#42527)
Signed-off-by: Jee Jee Li <jeejeelee@inferact.ai>
|
2026-05-18 03:04:31 -07:00 |
|
|
Harry Mellor
|
9537542537
|
Revert checkpoint specific workaround in Transformers modelling backend (#42923)
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
|
2026-05-18 17:31:06 +09:00 |
|
|
Rishapveer Singh
|
5ab6d1b3fd
|
[Model] [Perf] Use flatten for Qwen3.5's GDN output projection (#42311)
Signed-off-by: Rishapveer Singh <singhrishapveer@gmail.com>
|
2026-05-18 16:14:36 +08:00 |
|
|
gaozihao-shy
|
23c15acd77
|
[BugFix] Kimi-K2.5: skip vision tower dtype conversion when using quantization (#42869)
Signed-off-by: gaozihao-shy <gaozihao-shy@users.noreply.github.com>
Signed-off-by: gaozihao <gaozihao3@huawei.com>
|
2026-05-18 05:07:16 +00:00 |
|
|
Andreas Karatzas
|
b50646e5ef
|
[ROCm][CI] Stabilize ROCm pooling and multimodal CI (#42909)
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
|
2026-05-18 03:57:59 +00:00 |
|
|
Soyaazz
|
990f49bdcb
|
[MM][CG] Enable encoder Cudagraph for Step3VL (#42224)
Signed-off-by: JisoLya <523420504@qq.com>
Signed-off-by: Soyaazz <523420504@qq.com>
|
2026-05-17 20:19:13 -07:00 |
|
|
Yiliu Dongandqianlihuang
|
03ddc1c9bc
|
[Perf] Wire silu_and_mul_per_block_quant into TritonFP8MoE (MiniMax-M2) (#42497)
Signed-off-by: qianlihuang <yiliu.dong@qq.com>
Signed-off-by: Yiliu Dong <91178480+qianlihuang@users.noreply.github.com>
Co-authored-by: qianlihuang <yiliu.dong@qq.com>
|
2026-05-17 21:57:04 -04:00 |
|
|
TJian
|
599e75f432
|
[ROCm] [Bugfix] Fix DeepSeek V4 Functionality and Accuracy (#42810)
Signed-off-by: tjtanaa <tunjian.tan@embeddedllm.com>
|
2026-05-17 12:18:50 -04:00 |
|
|
Taneem Ibrahim
|
1c8e9c0399
|
Refactor: Pass num_labels explicitly to PoolerClassify instead of reading from global config (#42851)
Signed-off-by: Taneem Ibrahim <taneem.ibrahim@gmail.com>
|
2026-05-17 14:40:21 +00:00 |
|
|
zofiaandKunshang Ji
|
0fa888465e
|
[XPU] fix weight scale shape (#42725)
Signed-off-by: Zhu, Zufang <zufang.zhu@intel.com>
Co-authored-by: Kunshang Ji <kunshang.ji@intel.com>
|
2026-05-17 16:55:10 +08:00 |
|
|
weizhoublue
|
a94189295b
|
Fix Weight loading for Qwen3.5-MTP and Qwen3-VL using runai_streamer (#42716)
Signed-off-by: weizhoublue <weizhou.lan@daocloud.io>
|
2026-05-16 17:54:27 -07:00 |
|
|
Artem PerevedentsevandVadim Gimpelson
|
0867497368
|
[CI/Build] Bump flashinfer to v0.6.11.post2 (#41711)
Signed-off-by: Artem Perevedentsev <aperevedents@nvidia.com>
Co-authored-by: Vadim Gimpelson <156319763+vadiklyutiy@users.noreply.github.com>
|
2026-05-16 14:55:12 -07:00 |
|
|
Taneem Ibrahim
|
787bc0d031
|
Add unit tests for pooler activation functions (#42824)
Signed-off-by: Taneem Ibrahim <taneem.ibrahim@gmail.com>
|
2026-05-16 14:58:16 -04:00 |
|
|
weizhoublue
|
d1586e1a12
|
Fix: Propagate pinned model revisions into Ultravox secondary weight loading (#42830)
|
2026-05-16 17:02:54 +00:00 |
|
|
Jiangyun Zhu
|
8a56da3845
|
[Experimental] Breakable CUDA graph (#42304)
Signed-off-by: zjy0516 <riverclouds.zhu@qq.com>
|
2026-05-16 22:04:12 +08:00 |
|
|
Michael Goin
|
852f567444
|
[Bugfix] Respect explicit --kv-cache-dtype over checkpoint kv_cache_scheme (#42782)
Signed-off-by: mgoin <mgoin64@gmail.com>
|
2026-05-15 17:15:52 -07:00 |
|
|
Michael Goin
|
b2a27b82d9
|
[Kernel][UX] Add --linear-backend arg for linear kernel selection (#39538)
Signed-off-by: mgoin <mgoin64@gmail.com>
|
2026-05-15 17:07:39 -07:00 |
|
|
|
1ccdf87507
|
[Bugfix] Fix layerwise reload alias-buffer corruption (#42481)
Signed-off-by: rasdani <73563550+rasdani@users.noreply.github.com>
Co-authored-by: OpenAI Codex <codex@openai.com>
Co-authored-by: Roger Wang <hey@rogerw.io>
|
2026-05-15 15:20:53 -07:00 |
|
|
|
06d020bb6e
|
[Bugfix] Fix SM121 (DGX Spark) exclusion from Marlin/CUTLASS FP8 paths (#35568)
Signed-off-by: Blake Ledden <blake@secondnaturecomputing.com>
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
Co-authored-by: Pavani Majety <pmajety@nvidia.com>
|
2026-05-15 10:59:00 -07:00 |
|
|
Wentao Ye
|
491e8d8539
|
[Perf] Optimize MLA attention _v_up_proj bmm by removing additional copy (#42561)
Signed-off-by: yewentao256 <zhyanwentao@126.com>
|
2026-05-15 08:14:26 -07:00 |
|
|
L.B.R.andL.B.R.
|
d792d993c1
|
[ROCm] Widen OAI Triton MoE capability range to include gfx12 (RDNA4) (#37826)
Signed-off-by: L.B.R. <lbr@mmonad.com>
Co-authored-by: L.B.R. <lbr@mmonad.com>
|
2026-05-15 07:59:57 -07:00 |
|
|
Benjamin Chislett
|
0fe7550254
|
[Bugfix] DFlash FP8 KV-Cache (#42692)
Signed-off-by: Benjamin Chislett <bchislett@nvidia.com>
|
2026-05-15 08:29:45 -06:00 |
|
|
pmaybankandTJian
|
1dc3fe08ea
|
gemma3 multi-gpu bug-fix (#42630)
Signed-off-by: Philip Maybank <pmaybank@amd.com>
Co-authored-by: TJian <tunjian.tan@embeddedllm.com>
|
2026-05-15 02:32:05 -07:00 |
|
|
Juan Pérez de AlgabaandCyrus Leung
|
d26a28ab03
|
fix: propagate revision/code_revision pins to all artifact boundaries (#42616)
Signed-off-by: jperezde <jperezde@redhat.com>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>
|
2026-05-15 02:31:54 -07:00 |
|
|
bobofang_amdandTJian
|
ccde9540be
|
DeepSeekV4-Pro enable cuda graph full and piecewise mode (#42604)
Co-authored-by: TJian <tunjian.tan@embeddedllm.com>
|
2026-05-15 01:45:30 -07:00 |
|
|
Isotr0pyandzxy
|
faa4b76afa
|
[Model] Support InternS2 Preview (#42705)
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
Co-authored-by: zxy <46674730+CUHKSZzxy@users.noreply.github.com>
|
2026-05-14 21:30:26 -07:00 |
|
|
|
fa2a33b893
|
[Quant] Consolidate GPTQ: rename gptq_marlin.py to auto_gptq.py (#38288)
Signed-off-by: Chengyi Nie <cnie@roblox.com>
Co-authored-by: Chengyi Nie <cnie@roblox.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
|
2026-05-15 08:25:52 +08:00 |
|
|
Yongye ZhuandClaude
|
f8848b2f2d
|
[Bugfix] Add swiglu limits to deepgemm fp8 methods (#41986)
Signed-off-by: Yongye Zhu <zyy1102000@gmail.com>
Co-authored-by: Claude <noreply@anthropic.com>
|
2026-05-14 15:43:13 -07:00 |
|
|
Charlie Fu
|
4cfcc0866f
|
[CI][ROCm] Remove unsupported cases in test_fusion.py (#38680)
Signed-off-by: charlifu <charlifu@amd.com>
|
2026-05-14 17:37:18 -04:00 |
|
|
TresandCursor
|
f887aa1a53
|
[Aiter][ROCm] RMSNormGated+GroupedQuantFP8 fusion (#40710)
Signed-off-by: Tres Popp <tres.popp@amd.com>
Signed-off-by: Tres Popp <trespopp@gmail.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
|
2026-05-14 15:37:09 -04:00 |
|
|
Matthew Bonanni
|
9898f94abe
|
[Attention] Remove deprecated MLA prefill arguments (#42555)
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
|
2026-05-14 10:34:06 -07:00 |
|
|
Baorun (Lauren) Mu
|
a7737cb4f3
|
[Fix] Misc Fixes in ViT CUDA Graph (#38040)
Signed-off-by: Baorun Mu <bmu@nvidia.com>
|
2026-05-14 23:49:06 +08:00 |
|
|
Cyrus Leung
|
b8a25d0e12
|
[Bugfix] Fix LM detection for Nemotron Parse (#42641)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
|
2026-05-14 23:42:10 +08:00 |
|
|
|
c7560af424
|
[RFC] Replace shared-memory routed experts with ModelRunnerOutput transfer and HTTP support (#39568)
Signed-off-by: xhx1022 <1737006628@qq.com>
Signed-off-by: arlenxu <arlenxu@tencent.com>
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Co-authored-by: arlenxu <arlenxu@tencent.com>
Co-authored-by: Junjie Zhang <junj.jay.zhang@gmail.com>
|
2026-05-14 14:12:30 +00:00 |
|
|
|
0a65d46628
|
[DSV4] Fuse norm and router for low latency scenario (#41263)
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
Signed-off-by: jeejeelee <jeejeelee@verda-b300-05.datacrunch.io>
Co-authored-by: jeejeelee <jeejeelee@verda-b300-05.datacrunch.io>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
2026-05-14 05:11:02 -07:00 |
|