10789 Commits

Author SHA1 Message Date
Asaf Joseph Gardin
05181cc57f
[Hybrid] Add mamba_block_size to Engine Args (#27289)
Signed-off-by: asafg <39553475+Josephasafg@users.noreply.github.com>
2025-10-28 12:54:24 +00:00
Zhengxu Chen
259504e147
[compile] Add enable_prompt_embeds to compile hash. (#27285)
Signed-off-by: zhxchen17 <zhxchen17@fb.com>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>
2025-10-28 20:46:03 +08:00
Wentao Ye
0484b64248
[Bug] Fix shape issue for eplb expert weights (#27589)
Signed-off-by: yewentao256 <zhyanwentao@126.com>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>
2025-10-28 20:44:05 +08:00
Cyrus Leung
f58d9b6404
[Misc] Separate out utils.counter and move utils.Device to engine (#27588)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
2025-10-28 12:20:46 +00:00
Matthew Bonanni
44b5ce956d
[Bugfix] In LongRoPE, decide short vs long based on max_model_len (#27431)
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
2025-10-28 12:00:56 +00:00
Nick Hill
7a865f2325
[V0 Deprecation] Remove vestigial V0 logits_processors.py file (#27601)
Signed-off-by: Nick Hill <nhill@redhat.com>
2025-10-28 19:17:45 +08:00
wangln19
2fa90bda27
Fix a robust parsing issue in KimiK2ToolParser that causes IndexError (#27565)
Signed-off-by: wangln19 <wanglinian@dev.wanglinian.msh-dev.svc.cluster.local>
Co-authored-by: wangln19 <wanglinian@dev.wanglinian.msh-dev.svc.cluster.local>
2025-10-28 11:11:50 +00:00
Zhewen Li
0291fbf65c
[CI/Build] Fix amd model executor test (#27612)
Signed-off-by: zhewenli <zhewenli@meta.com>
2025-10-28 08:58:11 +00:00
Jialin Ouyang
b46e4a06f1
[Core][Bookkeeping Optimization] Update against numpy view of is_token_ids tensor (#27618)
Signed-off-by: Jialin Ouyang <Jialin.Ouyang@gmail.com>
2025-10-28 08:13:10 +00:00
Li, Jiang
d34f5fe939
[Bugfix][CPU] Fallback oneDNN linear to torch linear to fix half gemm support on legecy platforms (#27526)
Signed-off-by: jiang1.li <jiang1.li@intel.com>
Co-authored-by: Isotr0py <mozf@mail2.sysu.edu.cn>
2025-10-27 23:25:44 -07:00
Eric Yue
bdb01a38fe
[Hardware][AMD][Model] Triton MoE tuning configs for GLM-4.6 for MI300X (#27323)
Signed-off-by: minatoaquaMK2 <jiacheng.yue@foxmail.com>
2025-10-27 22:58:06 -07:00
vllmellm
5b3c35a68e
[ROCm] [Doc] Update ROCm installation docs (#27327)
Signed-off-by: vllmellm <vllm.ellm@embeddedllm.com>
2025-10-28 13:00:50 +08:00
Chauncey
61fbfe5274
[Bugfix] fixed inconsistent finish_reason handling between V0 and V1 engines (#27555)
Signed-off-by: chaunceyjiang <chaunceyjiang@gmail.com>
2025-10-28 02:18:08 +00:00
Kuntai Du
255e34ca50
[Stability fix] turn off HMA allocator when connector is set (#27592)
Signed-off-by: KuntaiDu <kuntai@uchicago.edu>
Signed-off-by: Kuntai Du <kuntai@uchicago.edu>
2025-10-27 18:32:23 -07:00
Roger Wang
a8d2e326ec
[Bugfix][CI] Fix config resolving logic with remote models (#27610) 2025-10-28 00:48:32 +00:00
Andrew Xia
53a56e658b
[gpt-oss][2/N] Support input_messages in responsesRequest (#26962)
Signed-off-by: Andrew Xia <axia@fb.com>
Co-authored-by: Andrew Xia <axia@fb.com>
2025-10-27 23:15:49 +00:00
usberkeley
69f064062b
Code quality improvements: version update, type annotation enhancement, and enum usage simplification (#27581)
Signed-off-by: Bradley <bradley.b.pitt@gmail.com>
2025-10-27 17:50:22 +00:00
Micah Williamson
921e78f4bb
[ROCm] Update AITER branch for ROCm base docker (#27586)
Signed-off-by: Micah Williamson <micah.williamson@amd.com>
2025-10-27 17:22:33 +00:00
Cyrus Leung
6ebffafbb6
[Misc] Clean up more utils (#27567)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
2025-10-27 15:30:38 +00:00
Ben Browning
3b96f85c36
[Chore]: Stream tokens vs characters in tool call parser tests (#26513)
Signed-off-by: Ben Browning <bbrownin@redhat.com>
2025-10-27 23:06:25 +08:00
tingtinggithub
23ad820553
fixing mm placeholder replacement issue with gemma3 (#27538)
Signed-off-by: tingtingtang1992 <streamttt@gmail.com>
2025-10-27 14:34:01 +00:00
Varun Sundar Rabindranath
5d3be3ba4c
[Bugfix][LoRA][FusedMoE] Select MxFP4 Backend based on LoRA Enablement (#27487)
Signed-off-by: Varun Sundar Rabindranath <vsundarr@redhat.com>
Co-authored-by: Varun Sundar Rabindranath <vsundarr@redhat.com>
2025-10-27 07:32:50 -07:00
Yu Jiaqi
4f882be4a0
[Model] Siglip2 Model Support (#27566)
Signed-off-by: piood <2477084691@qq.com>
2025-10-27 06:57:37 -07:00
Asaf Joseph Gardin
9273754222
[Hybrid] Added supports_mamba_prefix_caching Protocol (#27339)
Signed-off-by: asafg <39553475+Josephasafg@users.noreply.github.com>
2025-10-27 13:05:20 +00:00
Jee Jee Li
f4e8154076
[Kernel] Enable moe LoRA kernel support FP16 (#27468)
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
2025-10-27 19:48:37 +08:00
Fadi Arafeh
a663f6ae64
[cpu][perf] Fix low CPU utilization with VLLM_CPU_OMP_THREADS_BIND on AArch64 (#27415)
Signed-off-by: Fadi Arafeh <fadi.arafeh@arm.com>
2025-10-27 11:14:55 +00:00
Chauncey
a4fc21895e
[Bugfix] Fixed when return_token_ids=False, the first event still contains prompt_token_ids. (#27561)
Signed-off-by: chaunceyjiang <chaunceyjiang@gmail.com>
2025-10-27 11:06:43 +00:00
Shanshan Shen
a3e8611da5
[Bugfix] Limit the default value of max_model_len when it is not specified by users (#27556)
Signed-off-by: shen-shanshan <467638484@qq.com>
2025-10-27 10:16:20 +00:00
Cyrus Leung
7c2bdb83dc
[Misc] Clean up utils (#27552)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
2025-10-27 09:05:40 +00:00
Danielle Robinson
9932ed6a83
[Kernel] Adding split_K implementation for fused_moe_lora (#27291)
Signed-off-by: Danielle Robinson <dmmaddix@amazon.com>
Signed-off-by: Danielle Robinson <dcmaddix@gmail.com>
Co-authored-by: Danielle Robinson <dmmaddix@amazon.com>
Co-authored-by: Jee Jee Li <pandaleefree@gmail.com>
2025-10-27 02:05:24 -07:00
Jee Jee Li
2d631d28c6
[Doc] Slight improvement to M2 and beyond (#27554)
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
Co-authored-by: Roger Wang <hey@rogerw.io>
2025-10-27 09:02:10 +00:00
Cyrus Leung
b368382964
[Model] Deprecate merge_by_field_config=False (#27551)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
2025-10-27 16:43:00 +08:00
gnovack
a806c14cc7
[Performance][LoRA] add context varying params to 'do_not_specialize' in fused moe lora (#27445)
Signed-off-by: gnovack <gnovack@amazon.com>
2025-10-27 06:31:55 +00:00
yyzxw
181bf5bbde
[Docs] reemove the incorrect enable_reasoning parameter (#27550)
Signed-off-by: zxw <1020938856@qq.com>
2025-10-26 23:17:19 -07:00
Cyrus Leung
cbd5e07a51
[Model] Use merge_by_field_config for MM models (Qwen series) (#27546)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
2025-10-27 05:38:05 +00:00
CSWYF3634076
63b22e0dbb
[Model][Bugfix] fix ernie45 moe 300B SharedFusedMoE output tuple (#27316)
Signed-off-by: wangyafeng <wangyafeng@baidu.com>
2025-10-26 20:53:31 -07:00
Roger Young
5980604c44
Fix MiniMax-M2 copyright (#27537)
Signed-off-by: xuebi <xuebi@minimaxi.com>
Co-authored-by: xuebi <xuebi@minimaxi.com>
2025-10-27 03:29:51 +00:00
youkaichao
361a7463d3
fix m2 test (#27536)
Signed-off-by: youkaichao <youkaichao@gmail.com>
2025-10-27 01:04:36 +08:00
Roger Young
720af6ab79
[Model][MiniMax-M2] Support MiniMax-M2 Model (#27535)
Signed-off-by: xuebi <xuebi@minimaxi.com>
Co-authored-by: xuebi <xuebi@minimaxi.com>
2025-10-27 00:59:11 +08:00
Cyrus Leung
55cba4a05c
[CI/Build] Update causal-conv1d installation (#27529)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
2025-10-26 22:14:22 +08:00
Cyrus Leung
c7abff2990
Revert "[CI/Build] Use CPU for mm processing test on CI (#27522)" (#27531)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
2025-10-26 04:44:27 -07:00
Yeshwanth N
71b1c8b667
[Chore]:Extract math and argparse utilities to separate modules (#27188)
Signed-off-by: Yeshwanth Surya <yeshsurya@gmail.com>
Signed-off-by: Yeshwanth N <yeshsurya@gmail.com>
Signed-off-by: yeshsurya <yeshsurya@gmail.com>
2025-10-26 04:03:32 -07:00
Cyrus Leung
8fb7b2fab9
[Doc] Fix links to GH projects (#27530)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
2025-10-26 17:55:51 +08:00
Cyrus Leung
be7b55a83d
[Doc] Remove Molmo warning (#27527)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
2025-10-26 16:22:52 +08:00
Lucia Fang
315b860abe
[bugfix]fix empty prompts for async-engine mode in benchmark throughput (#27494)
Signed-off-by: Lucia Fang <fanglu@fb.com>
2025-10-26 08:16:35 +00:00
rongfu.leng
87c41c26ad
[Bugfix] Fix processor initialization for model from modelscope instead of HF (#27461)
Signed-off-by: rongfu.leng <rongfu.leng@daocloud.io>
Co-authored-by: Isotr0py <mozf@mail2.sysu.edu.cn>
2025-10-26 07:44:31 +00:00
JartX
65d2cf9511
[BUGFIX][ROCM] ViT FlashAttention on ROCm (no GFX9) and contiguous on qwen3vl ROCm TORCH_SDPA (#27190)
Signed-off-by: JartX <sagformas@epdcenter.es>
Co-authored-by: tjtanaa <tunjian.tan@embeddedllm.com>
2025-10-26 15:08:52 +08:00
Isotr0py
d63cd9ff10
[CI/Build] Use CPU for mm processing test on CI (#27522)
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
2025-10-26 13:09:18 +08:00
Cyrus Leung
66a168a197
[CI/Build] Refactor processing tests (#27470)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
Co-authored-by: Isotr0py <mozf@mail2.sysu.edu.cn>
2025-10-25 16:14:30 +00:00
Matthew Bonanni
a99564ac5b
[Attention] Add missing kv cache scale setup (#27490)
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
2025-10-25 00:12:49 -07:00