biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity
14,061 Commits 2 Branches 140 Tags
ea37530b474fa738a99a53a8975af4e389b968c7
Commit Graph

14061 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
Harry Mellor
a39dd7bb06 [CI] Skip "Multi-Modal Models Test (Extended) 3" test that's broken in current Transformers (#28559) 
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
 2025-11-12 19:38:13 +00:00
Thomas Parnell
64d57c3be7 [Model] [Config] Correctly identify granite-4.0-micro as non-hybrid model (#28563) 
Signed-off-by: Thomas Parnell <tpa@zurich.ibm.com>
 2025-11-12 18:17:55 +00:00
PerryZhang01
a1e7fa362a [EPLB][ROCm]: support EPBL for ROCm backend (#27731) 
Signed-off-by: Perry Zhang <perzhang@amd.com>
Co-authored-by: Perry Zhang <perzhang@amd.com>
 2025-11-12 18:16:35 +00:00
alberto
bac904565f Implement ARC KV cache eviction policy for CPU offloader (#27039) 
Signed-off-by: Alberto Perdomo <aperdomo@redhat.com>
Signed-off-by: alberto <aperdomo@redhat.com>
Co-authored-by: Or Ozeri <or@ozery.com>
 2025-11-12 09:51:39 -08:00
Benjamin Chislett
304419576a [Perf] Refactor cudagraph_support to enable full CUDA graphs for spec decoding with FlashInfer (#28479) 
Signed-off-by: Benjamin Chislett <bchislett@nvidia.com>
 2025-11-13 01:56:40 +09:00
Harry Mellor
a742134cc5 Remove deprecated fields from CompilationConfig (#27593) 
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
 2025-11-12 16:10:28 +00:00
Nicolò Lucchesi
728a9eb70e [Misc] Refactor Attention kv transfer methods into decorator (#27816) 
Signed-off-by: NickLucche <nlucches@redhat.com>
Signed-off-by: Mark McLoughlin <markmc@redhat.com>
Co-authored-by: Mark McLoughlin <markmc@redhat.com>
 2025-11-12 16:05:44 +00:00
Canlin Guo
bc5bd45c7d [Refactor] Remove redundant TP gather/split in split_qkv in QwenVL (#28271) 
Signed-off-by: gcanlin <canlinguosdu@gmail.com>
 2025-11-12 15:56:47 +00:00
Alexander Matveev
f76e85c299 [Performance][Hopper] Avoid M dim padding to 4x for most cases (due to cuda graphs paddings) (#28492) 
Signed-off-by: Alexander Matveev <amatveev@redhat.com>
 2025-11-12 10:51:43 -05:00
Harry Mellor
54aecd9ed5 Fix pre-commit (and XPU) on main (#28556) 
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
 2025-11-12 06:13:41 -08:00
wangxiyuan
10138c92a5 [V0 deprecation] Deprecate use_v1 parameter (#28112) 
Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>
 2025-11-12 14:03:52 +00:00
Jee Jee Li
a9d18b5107 [Bugfix] Fix gpt_oss packed_modules_mapping (#28536) 
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
 2025-11-12 21:02:06 +08:00
TJian
edb59a9470 [ROCm] [Bugfix] Fix fused_qknorm_rope_kernel rocm compatibility (#28500) 
Signed-off-by: tjtanaa <tunjian.tan@embeddedllm.com>
 2025-11-12 05:01:14 -08:00
ZhengHongming888
c5f10cc139 add cpu option for p/d in nixl_connector (#28356) 
Signed-off-by: Hongming Zheng <hongming.zheng@intel.com>
 2025-11-12 11:53:08 +00:00
ziruiliu
d143152308 [KVConnector] Enable get_block_ids_with_load_errors() in LMCache connector (#27978) 
Signed-off-by: Zirui Liu <ziliu@ddn.com>
Signed-off-by: ziruiliu <ziliu@ddn.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
Co-authored-by: Nicolò Lucchesi <nlucches@redhat.com>
 2025-11-12 11:44:58 +01:00
Chaojun Zhang
a4730c1b4f [XPU]Fix crash due to removed VLLM_USE_V1 attribute (#28520) 
Signed-off-by: chaojun-zhang <chaojun.zhang@intel.com>
 2025-11-12 10:20:55 +00:00
wuyaoxuehun
d3ade61e42 [Model] fix glm4_moe_mtp load weights with GLM-4.6 checkpoint. (#27597) 
Signed-off-by: wuao.scotty <wuao.scotty@bytedance.com>
Co-authored-by: wuao.scotty <wuao.scotty@bytedance.com>
 2025-11-12 10:14:00 +00:00
yyzxw
1761dea1a8 [BugFix]: --enable-lora with model granite-4.0-micro crash (#27733) 
Signed-off-by: zxw <1020938856@qq.com>
 2025-11-12 09:03:56 +00:00
Huamin Li
c748355e0d [CI] Introduce autorun_on_main feature (#27836) 
Signed-off-by: Huamin Li <3ericli@gmail.com>
 2025-11-12 08:51:19 +00:00
Chenguang Zheng
91864b79b3 [CI/Build] Fix crash due to removed VLLM_USE_V1 attribute in EPD (#28521) 
Signed-off-by: knlnguyen1802 <knlnguyen1802@gmail.com>
Co-authored-by: knlnguyen1802 <knlnguyen1802@gmail.com>
Co-authored-by: Roger Wang <hey@rogerw.io>
 2025-11-11 23:09:33 -08:00
Lukas Geiger
ac0bb2c307 [Core] Cache vllm_is_batch_invariant (#28304) 
Signed-off-by: Lukas Geiger <lukas.geiger94@gmail.com>
 2025-11-12 05:03:01 +00:00
ai-jz
f31419ed8b [Benchmark] Add retry support to fix workload bias in multi-turn benchmark (#28493) 2025-11-12 05:00:45 +00:00
Fanli Lin
b9ce9a3013 [BugFix] Add fallback path in apply_rotary_pos_emb_flashattn for non-cuda platforms (#28447) 
Signed-off-by: Lin, Fanli <fanli.lin@intel.com>
 2025-11-12 03:13:21 +00:00
Chenguang Zheng
4ccffe561f [Core] Encoder separation for Encode-Prefill-Decode Disaggregation (#25233) 
Signed-off-by: n00909098 <nguyen.kha.long@huawei.com>
Signed-off-by: knlnguyen1802 <knlnguyen1802@gmail.com>
Signed-off-by: herotai214 <herotai214@gmail.com>
Signed-off-by: Khuong Le <khuong.le.manh@huawei.com>
Signed-off-by: Khuong Le <lemanhkhuong2611@gmail.com>
Co-authored-by: n00909098 <nguyen.kha.long@huawei.com>
Co-authored-by: knlnguyen1802 <knlnguyen1802@gmail.com>
Co-authored-by: herotai214 <herotai214@gmail.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
Co-authored-by: Khuong Le <khuong.le.manh@huawei.com>
Co-authored-by: Khuong Le <lemanhkhuong2611@gmail.com>
 2025-11-11 18:58:33 -08:00
Lukas Geiger
cbb799e314 [Model][Qwen3VL] Simplify get_mrope_input_positions using numpy (#28302) 
Signed-off-by: Lukas Geiger <lukas.geiger94@gmail.com>
 2025-11-12 02:55:10 +00:00
Andreas Karatzas
9f0247cfa4 VLLM_USE_TRITON_FLASH_ATTN V0 variable deprecation (#27611) 
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
Signed-off-by: Andreas Karatzas <Andreas.Karatzas@amd.com>
 2025-11-11 18:34:36 -08:00
Li, Jiang
7f829be7d3 [CPU] Refactor CPU attention backend (#27954) 
Signed-off-by: jiang1.li <jiang1.li@intel.com>
 2025-11-12 09:43:06 +08:00
wangxiyuan
e1710393c4 [[V0 deprecation]]Remove VLLM_USE_V1 env (#28204) 
Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>
 2025-11-11 18:22:16 -07:00
Isotr0py
3f770f4427 [Performance] Cache loaded custom logitsprocs to avoid overheads (#28462) 
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
 2025-11-11 16:49:29 -08:00
Yanan Cao
48c879369f [Frontend] Change CompilationMode to a proper Enum (#28165) 
Signed-off-by: Yanan Cao <gmagogsfm@gmail.com>
 2025-11-11 19:46:18 -05:00
Ilya Markov
1788aa1efb [BugFix] Graceful handling of torch symm mem errors. (#27671) 
Signed-off-by: ilmarkov <markovilya197@gmail.com>
Co-authored-by: Michael Goin <mgoin64@gmail.com>
 2025-11-11 17:41:54 -07:00
Adrian Abeyta
d23539549a Use FLASHINFER MLA backend when testing fp8_kv_scale_compile (#28491) 
Signed-off-by: adabeyta <aabeyta@redhat.com>
 2025-11-12 00:34:58 +00:00
Max Hu
412e153df5 [Feature] Allow configuring FlashInfer workspace size (#28269) 
Signed-off-by: Max Hu <hyoung2991@gmail.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
 2025-11-11 23:32:20 +00:00
Michael Goin
e5f599d4d1 [Bugfix] Disable shared expert overlap if Marlin MoE is used (#28410) 
Signed-off-by: mgoin <mgoin64@gmail.com>
 2025-11-11 23:16:12 +00:00
Michael Goin
28534b92b9 Add Zurich vLLM Meetup (#28488) 
Signed-off-by: mgoin <mgoin64@gmail.com>
 2025-11-11 14:53:59 -08:00
wangxiyuan
d4902ba56d [Misc] Cleanup Executor interface (#28441) 
Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>
 2025-11-11 22:28:07 +00:00
Kyuyeun Kim
df4d3a44a8 [TPU] Rename path to tpu platform (#28452) 
Signed-off-by: Kyuyeun Kim <kyuyeunk@google.com>
 2025-11-11 19:16:47 +00:00
Jee Jee Li
9d1c474704 [LoRA][1/N]Remove LoRA extra vocab (#28382) 
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
 2025-11-11 11:06:21 -08:00
Jie Luo
8c32c6e4b4 [Misc] fix typo in DCP comment (#28389) 
Signed-off-by: Livinfly <luojie3m@gmail.com>
 2025-11-11 10:59:16 -08:00
Canlin Guo
de120bc94f [V0 deprecation] Clean up num_prefill_tokens logic for V0 (#28203) 
Signed-off-by: gcanlin <canlinguosdu@gmail.com>
 2025-11-11 10:57:12 -08:00
Jialin Ouyang
4228be7959 [Perf] Use np.ndarray instead of list[list[int]] to reduce GC overhead (#28245) 
Signed-off-by: Jialin Ouyang <Jialin.Ouyang@gmail.com>
 2025-11-11 10:28:47 -08:00
Lukas Geiger
76e4dcf225 [Misc] Remove unused attention prefix prefill ops functions (#26971) 
Signed-off-by: Lukas Geiger <lukas.geiger94@gmail.com>
 2025-11-11 18:26:04 +00:00
Fanli Lin
d5edcb8678 [BugFix] Fix Siglip2Attention on XPU (#28448) 
Signed-off-by: Lin, Fanli <fanli.lin@intel.com>
 2025-11-11 18:18:02 +00:00
Xin Yang
6c3c0f8235 [Kernel] Optimize rms_norm kernel (#27931) 
Signed-off-by: Xin Yang <xyangx@amazon.com>
 2025-11-11 18:02:23 +00:00
Matthew Bonanni
684f254585 Prefer FlashAttention MLA as default over FlashMLA (#27363) 
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
 2025-11-11 17:13:51 +00:00
Zhewen Li
e553424919 [CI/Build] Refactor Attention backend for test_prefix_prefill from xformers to SDPA (#28424) 
Signed-off-by: zhewenli <zhewenli@meta.com>
Signed-off-by: Roger Wang <hey@rogerw.io>
Co-authored-by: Roger Wang <hey@rogerw.io>
 2025-11-12 01:09:47 +08:00
xuebwang-amd
5a1271d83a [Quantization] fix attention quantization of gpt_oss model (#27334) 
Signed-off-by: xuebwang-amd <xuebwang@amd.com>
 2025-11-11 12:06:00 -05:00
xuebwang-amd
05576df85c [ROCm][Quantization] extend AMD Quark to support mixed-precision quantized model (#24239) 
Signed-off-by: xuebwang-amd <xuebwang@amd.com>
Co-authored-by: fxmarty-amd <felmarty@amd.com>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>
 2025-11-11 12:05:22 -05:00
zhrrr
68c09efc37 [Kernel][Perf] fuse QK Norm and RoPE into one cuda kernel for Qwen Model (#27165) 
Signed-off-by: zhuhaoran <zhuhaoran.zhr@alibaba-inc.com>
 2025-11-11 12:00:31 -05:00
Nicolò Lucchesi
a7ef3eb0cd [NIXL] Generalize block-first backend layouts (FlashInfer-like) (#28282) 2025-11-11 16:57:43 +00:00