2142035b51
[V1] Support multiple kv connectors ( #17564 )
...
Signed-off-by: mgoin <mgoin64@gmail.com>
Signed-off-by: Nick Hill <nhill@redhat.com>
Co-authored-by: Nick Hill <nhill@redhat.com>
2025-05-14 16:28:02 -07:00
78aa341d12
[CI] Fix race condition in test_kv_cache_events test ( #18169 )
...
Signed-off-by: Russell Bryant <rbryant@redhat.com>
2025-05-14 16:27:48 -07:00
7974736740
Add support for loading torchao models with `AOPerModuleConfig` ( #17826 )
...
Signed-off-by: Jerry Zhang <jerryzh168@gmail.com>
2025-05-14 16:24:59 -07:00
2fc9075b82
[V1] Structured Outputs + Thinking compatibility ( #16577 )
...
Signed-off-by: Aaron Pham <contact@aarnphm.xyz>
Co-authored-by: Russell Bryant <rbryant@redhat.com>
2025-05-14 15:45:24 -07:00
d93c976a0d
[Kernel] Have rotary embeddings support tensors ( #18046 )
...
Signed-off-by: Lucas Wilkinson <lwilkinson@neuralmagic.com>
2025-05-14 15:43:55 -07:00
856865008e
[CI] Disable Failing Tests ( #18165 )
2025-05-14 13:49:56 -07:00
f9c069c85e
Modularize fused experts and integrate PPLX kernels ( #15956 )
2025-05-14 13:11:54 -07:00
59dd311cf5
[KVConnector] Keep KVTransferParams as a dict ( #18033 )
2025-05-14 08:05:57 -07:00
d066e52013
[Bugfix] Fix chat utils tests ( #18139 )
...
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
2025-05-14 05:38:21 -07:00
d62a076e84
[Model] GritLM supports other attention backends ( #18109 )
...
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
2025-05-14 03:33:19 -07:00
259127f8b8
[Bugfix] Fix LoRA test ( #18123 )
...
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
2025-05-14 10:25:47 +00:00
612c2edb4f
[FEAT] [ROCm]: Add AITER CK 2 Stages MoE support ( #17110 )
...
Signed-off-by: tjtanaa <tunjian.tan@embeddedllm.com>
Co-authored-by: Gregory Shtrasberg <Gregory.Shtrasberg@amd.com>
2025-05-14 03:03:11 -07:00
82e7f9bb03
[Misc] replace does not exist model ( #18119 )
...
Signed-off-by: rongfu.leng <rongfu.leng@daocloud.io>
2025-05-14 02:13:47 -07:00
8f5dc41481
[Bugfix] Fix entrypoints audio test failure ( #18111 )
...
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
2025-05-14 09:08:07 +00:00
63ad622233
[New Model]: support GTE NewModel ( #17986 )
2025-05-14 01:31:31 -07:00
6685890d11
[Fix] Move "model_config" as keyword args in chat_utils.py ( #18098 )
...
Signed-off-by: Linkun <github@lkchen.net>
2025-05-13 23:27:26 -07:00
7b2f28deba
[AMD][torch.compile] Enable silu+fp8_quant fusion for rocm ( #18082 )
...
Signed-off-by: charlifu <charlifu@amd.com>
2025-05-13 22:13:56 -07:00
2d912fb66f
[FEAT] [ROCm] [V1]: Add AITER biased group topk for DeepSeekV3 ( #17955 )
...
Signed-off-by: tjtanaa <tunjian.tan@embeddedllm.com>
Co-authored-by: tjtanaa <tunjian.tan@embeddedllm.com>
2025-05-13 22:03:47 -07:00
f2ae883b67
[v1][KVCacheManager] pass num_new_computed_tokens to kv cache manager ( #18001 )
...
Signed-off-by: Chen Zhang <zhangch99@outlook.com>
2025-05-13 19:09:39 -07:00
40de1ef455
[FEAT] [ROCm]: Add AITER Block-Scaled GEMM Feature ( #14968 )
...
Signed-off-by: vllmellm <vllm.ellm@embeddedllm.com>
Signed-off-by: tjtanaa <tunjian.tan@embeddedllm.com>
Co-authored-by: tjtanaa <tunjian.tan@embeddedllm.com>
2025-05-13 19:08:20 -07:00
55aa7af994
[V1] DP scale-out (2/N): Decouple engine process management and comms ( #15977 )
...
Signed-off-by: Nick Hill <nhill@redhat.com>
2025-05-13 10:48:21 -07:00
cb528d0585
[Fix] check to make sure processor has chat templates ( #18047 )
...
Signed-off-by: Aaron Pham <contact@aarnphm.xyz>
2025-05-13 03:04:10 -07:00
ea6ae8cb45
[Bugfix] Fix marlin moe fallback logic for llama4 ( #18042 )
...
Signed-off-by: mgoin <mgoin64@gmail.com>
2025-05-13 07:53:28 +00:00
f0d610a8ae
[v1][KVCacheManager] Avoid full cache hit by controlling max_length ( #17999 )
...
Signed-off-by: Chen Zhang <zhangch99@outlook.com>
Co-authored-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
2025-05-13 06:50:38 +00:00
dc1a821768
[Feature][V1] Support `tool_choice: required` when using Xgrammar as the `StructuredOutputBackend`. ( #17845 )
...
Signed-off-by: chaunceyjiang <chaunceyjiang@gmail.com>
2025-05-12 23:01:31 -07:00
f6518b2b48
[ROCm] Skip tests for quantizations incompatible with ROCm ( #17905 )
...
Signed-off-by: Hissu Hyvarinen <hissu.hyvarinen@amd.com>
2025-05-12 18:39:28 -06:00
acee8f48aa
[Model] Support MiMo-7B inference with MTP ( #17433 )
...
Signed-off-by: wp-alpha <wangpeng66@xiaomi.com>
Co-authored-by: wangpeng66 <wangpeng66@xiaomi.com>
2025-05-12 23:25:33 +00:00
dc9905368d
[V1][Spec Decode] Eagle unit tests ( #17350 )
...
Signed-off-by: wwl2755 <wangwenlong2755@gmail.com>
2025-05-12 23:01:17 +00:00
ebab1ac37c
[CI] Make JSON output tests less likely to fail ( #17859 )
...
Signed-off-by: Russell Bryant <rbryant@redhat.com>
2025-05-12 22:31:54 +00:00
98ea35601c
[Lora][Frontend]Add default local directory LoRA resolver plugin. ( #16855 )
...
Signed-off-by: jberkhahn <jaberkha@us.ibm.com>
2025-05-12 10:39:10 -07:00
d19110204c
[P/D] NIXL Integration ( #17751 )
...
Signed-off-by: ApostaC <yihua98@uchicago.edu>
Signed-off-by: Tyler Michael Smith <tyler@neuralmagic.com>
Signed-off-by: rshaw@neuralmagic.com <robertgshaw2@gmail.com>
Signed-off-by: Robert Shaw <rshaw@neuralmagic.com>
Signed-off-by: mgoin <mgoin64@gmail.com>
Signed-off-by: Nick Hill <nhill@redhat.com>
Signed-off-by: Brent Salisbury <bsalisbu@redhat.com>
Co-authored-by: Tyler Michael Smith <tyler@neuralmagic.com>
Co-authored-by: ApostaC <yihua98@uchicago.edu>
Co-authored-by: Robert Shaw <rshaw@neuralmagic.com>
Co-authored-by: mgoin <mgoin64@gmail.com>
Co-authored-by: Nick Hill <nhill@redhat.com>
Co-authored-by: Tyler Michael Smith <tysmith@redhat.com>
Co-authored-by: Brent Salisbury <bsalisbu@redhat.com>
2025-05-12 09:46:16 -07:00
05a4324f8e
Initialize the delta tool call fields explicitly ( #17340 )
...
Signed-off-by: Max de Bayser <mbayser@br.ibm.com>
Co-authored-by: igmainc <igmainc@icloud.com>
2025-05-12 13:28:58 +00:00
08bf784078
[Bugfix] validate grammar and throw 400 error instead of crashing the engine when xgrammar validation fails ( #17623 )
...
Signed-off-by: Jason Cheng <jasoncky96@gmail.com>
Co-authored-by: Russell Bryant <rbryant@redhat.com>
2025-05-12 09:06:10 +08:00
021c16c7ca
[Model] Broadcast Ovis2 implementation to fit Ovis1.6 ( #17861 )
...
Signed-off-by: Isotr0py <2037008807@qq.com>
2025-05-11 17:56:30 -07:00
a810b5b088
[BugFix] [ROCm]: Bugfix and handle addition case of input for `rocm_aiter_rms_norm` ( #17857 )
...
Signed-off-by: tjtanaa <tunjian.tan@embeddedllm.com>
2025-05-11 04:17:11 -07:00
e4b8713380
[New Model]: nomic-embed-text-v2-moe ( #17785 )
2025-05-11 00:59:43 -07:00
cd3edfc908
[Misc] Add compressed-tensors NVFP4A16 emulation support ( #17914 )
...
Signed-off-by: Dipika Sikka <dipikasikka1@gmail.com>
Signed-off-by: Dipika <dipikasikka1@gmail.com>
2025-05-11 15:58:38 +08:00
9cea90eab4
[Frontend] Add /classify endpoint ( #17032 )
...
Signed-off-by: Frieda (Jingying) Huang <jingyingfhuang@gmail.com>
2025-05-11 07:57:07 +00:00
8132365b74
[Bugfix]: v1 engine - consider lora adapters in allowed_token_ids ( #17855 )
...
Signed-off-by: Ben Browning <bbrownin@redhat.com>
2025-05-11 00:53:58 -07:00
d74e5f37bc
[Kernel] fp4 marlin kernel ( #17687 )
...
Signed-off-by: Jinzhen Lin <linjinzhen@hotmail.com>
2025-05-10 19:58:49 -07:00
ca66a1674c
[v1] Rename specialized_manager.py to single_type_kv_cache_manager.py ( #17946 )
...
Signed-off-by: Chen Zhang <zhangch99@outlook.com>
2025-05-10 16:14:12 -07:00
950751a987
[v1] Pass BlockTable and KVCacheSpec to AttentionMetadataBuilders ( #17483 )
...
Signed-off-by: Chen Zhang <zhangch99@outlook.com>
2025-05-10 16:12:04 -07:00
fc4441a4ee
Add missing content type headers to /ping and /health ( #17036 ) ( #17786 )
...
Signed-off-by: Ximo Guanter <ximo.guanter@gmail.com>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
2025-05-10 07:13:32 +01:00
246e3e0a36
fix broken test vllm:test_kernels - test_attention_selector.py::test_flash_attn ( #17873 )
...
Co-authored-by: Stephen Chen <tracelog@meta.com>
2025-05-10 10:46:54 +08:00
0c0fdae84f
[Hardware/NVIDIA/Kernel] Enable nvidia/DeepSeek-R1-FP4 Model ( #16362 )
2025-05-09 16:24:41 -07:00
4b2ed7926a
Improve configs - the rest! ( #17562 )
...
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
2025-05-09 15:18:44 -07:00
6e5595ca39
[CI/Build] Automatically retry flaky tests ( #17856 )
...
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
2025-05-09 09:55:17 -06:00
200da9a517
[v1] Move block management logic from KVCacheManager to SpecializedManager ( #17474 )
...
Signed-off-by: Chen Zhang <zhangch99@outlook.com>
2025-05-09 15:25:34 +00:00
c6798baa9c
Change `top_k` to be disabled with `0` (still accept `-1` for now) ( #17773 )
...
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
2025-05-09 10:01:49 +00:00
d310e6de98
[BUGFIX]: return fast when request requires prompt logprobs ( #17251 )
2025-05-08 21:25:41 -07:00
3c9396a64f
[FEAT][ROCm]: Support AITER MLA on V1 Engine ( #17523 )
...
Signed-off-by: vllmellm <vllm.ellm@embeddedllm.com>
Co-authored-by: qli88 <qiang.li2@amd.com>
Co-authored-by: Hongxia Yang <62075498+hongxiayang@users.noreply.github.com>
2025-05-09 10:42:05 +08:00
376786fac1
Add cutlass support for blackwell fp8 blockwise gemm ( #14383 )
...
Signed-off-by: Shu Wang <shuw@nvidia.com>
2025-05-08 15:09:55 -07:00
ec54d73c31
[CI] Fix test_collective_rpc ( #17858 )
...
Signed-off-by: Russell Bryant <rbryant@redhat.com>
2025-05-08 16:47:12 +00:00
bb239a730f
[Bugfix] Fix quark fp8 format loading on AMD GPUs ( #12612 )
...
Signed-off-by: Felix Marty <felmarty@amd.com>
Signed-off-by: kewang2 <kewang2@amd.com>
Co-authored-by: kewang2 <kewang2@amd.com>
2025-05-08 02:53:53 -07:00
a463555dee
[TPU] Fix the test_sampler ( #17820 )
2025-05-08 05:51:33 -04:00
96722aa81d
[Frontend] Chat template fallbacks for multimodal models ( #17805 )
...
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
2025-05-07 23:05:54 -07:00
5a499e70d5
[Kernel][Hardware][AMD] Bf16 mfma opt for ROCm skinny GEMMs ( #17071 )
...
Signed-off-by: Hashem Hashemi <hashem.hashemi@amd.com>
Signed-off-by: charlifu <charlifu@amd.com>
Co-authored-by: charlifu <charlifu@amd.com>
2025-05-07 22:34:49 -07:00
6930a41116
[V1] Add VLLM_ALLOW_INSECURE_SERIALIZATION env var ( #17490 )
...
Signed-off-by: Russell Bryant <rbryant@redhat.com>
Signed-off-by: Nick Hill <nhill@redhat.com>
Co-authored-by: Nick Hill <nhill@redhat.com>
2025-05-08 13:34:02 +08:00
7ea2adb802
[Core] Support full cuda graph in v1 ( #16072 )
...
Signed-off-by: Chanh Nguyen <cnguyen@linkedin.com>
Co-authored-by: Chanh Nguyen <cnguyen@linkedin.com>
2025-05-07 22:30:15 -07:00
d43f914d42
[Core][Feature] Input metadata dump on crash ( #13407 )
...
Signed-off-by: Wallas Santos <wallashss@ibm.com>
2025-05-07 22:15:09 +00:00
c20ef40fd0
[Hardware][TPU][V1] Multi-LoRA implementation for the V1 TPU backend ( #14238 )
...
Signed-off-by: Akshat Tripathi <akshat@krai.ai>
Signed-off-by: Chengji Yao <chengjiyao@google.com>
Co-authored-by: Chengji Yao <chengjiyao@google.com>
2025-05-07 16:28:47 -04:00
db593aa67f
[Quantization] Quark MXFP4 format loading ( #16943 )
2025-05-07 15:05:05 -04:00
f98e307588
[Bugfix] Fix missing lora name mapping for lora without prefix ( #17793 )
...
Signed-off-by: Isotr0py <2037008807@qq.com>
2025-05-07 16:17:12 +00:00
be8ff88e66
[Bugfix] Fix Video IO error for short video ( #17791 )
...
Signed-off-by: Isotr0py <2037008807@qq.com>
2025-05-07 15:36:06 +00:00
98c89e16ff
Make key optional for rotary embedding ( #17566 )
...
Signed-off-by: Yong Hoon Shin <yhshin@meta.com>
2025-05-07 00:11:46 -07:00
324a3119b0
Fix test_memory_usage_no_spec ( #17754 )
...
Signed-off-by: Yong Hoon Shin <yhshin@meta.com>
2025-05-07 00:10:33 -07:00
8a15c2603a
[Frontend] Add missing chat templates for various MLLMs ( #17758 )
...
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
2025-05-07 00:10:01 -07:00
043e4c4955
Add NeuronxDistributedInference support, Speculative Decoding, Dynamic on-device sampling ( #16357 )
...
Signed-off-by: Satyajith Chilappagari <satchill@amazon.com>
Co-authored-by: Aaron Dou <yzdou@amazon.com>
Co-authored-by: Shashwat Srijan <sssrijan@amazon.com>
Co-authored-by: Chongming Ni <chongmni@amazon.com>
Co-authored-by: Amulya Ballakur <amulyaab@amazon.com>
Co-authored-by: Patrick Lange <patlange@amazon.com>
Co-authored-by: Elaine Zhao <elaineyz@amazon.com>
Co-authored-by: Lin Lin Pan <tailinpa@amazon.com>
Co-authored-by: Navyadhara Gogineni <navyadha@amazon.com>
Co-authored-by: Yishan McNabb <yishanm@amazon.com>
Co-authored-by: Mrinal Shukla <181322398+mrinalks@users.noreply.github.com>
2025-05-07 00:07:30 -07:00
1a45a61387
[Kernel] GGUF MoeVec kernel ( #16780 )
...
Signed-off-by: SzymonOzog <szymon.ozog@aleph-alpha.com>
Signed-off-by: SzymonOzog <szymon.ozog@gmail.com>
Signed-off-by: Isotr0py <2037008807@qq.com>
Co-authored-by: Isotr0py <2037008807@qq.com>
2025-05-06 23:07:23 -07:00
822de7fb94
[Misc] Split model loader ( #17712 )
...
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
2025-05-07 12:42:26 +08:00
e50a1f1a9c
[TPU] Add kernel test for moe_pallas ( #17496 )
...
Signed-off-by: Michael Goin <mgoin64@gmail.com>
2025-05-06 17:59:57 -07:00
18dd5e01f2
[Model] Mamba2 causal conv1d Refactor to Split Prefill and Decode Requests for Corresponding Kernels ( #17146 )
...
Signed-off-by: Chih-Chieh-Yang <7364402+cyang49@users.noreply.github.com>
2025-05-06 17:59:30 -07:00
2f925e5777
[Kernel] Unified Triton kernel that doesn't distinguish between prefill + decode ( #16828 )
...
Signed-off-by: Thomas Parnell <tpa@zurich.ibm.com>
Signed-off-by: Lucas Wilkinson <lwilkinson@neuralmagic.com>
Co-authored-by: Lucas Wilkinson <lwilkinson@neuralmagic.com>
2025-05-06 18:21:48 -04:00
aabcd2cae3
[v1] Introduce KVCacheBlocks as interface between Scheduler and KVCacheManager ( #17479 )
...
Signed-off-by: Chen Zhang <zhangch99@outlook.com>
2025-05-06 08:50:34 -07:00
a6fed02068
[V1][PP] Support PP for MultiprocExecutor ( #14219 )
...
Signed-off-by: jiang1.li <jiang1.li@intel.com>
Signed-off-by: jiang.li <jiang1.li@intel.com>
2025-05-06 07:58:05 -07:00
f9bc5a0693
[Bugfix] Fix triton import with local TritonPlaceholder ( #17446 )
...
Signed-off-by: Mengqing Cao <cmq0113@163.com>
2025-05-06 17:53:09 +08:00
6eae34533a
[Misc] Fix ScalarType float4 naming ( #17690 )
...
Signed-off-by: Lucas Wilkinson <lwilkinson@neuralmagic.com>
2025-05-06 01:07:15 -07:00
999328be0d
[Model] Add GraniteMoeHybrid 4.0 model ( #17497 )
...
Signed-off-by: Thomas Ortner <boh@zurich.ibm.com>
Signed-off-by: Stanislaw Wozniak <stw@zurich.ibm.com>
Co-authored-by: Thomas Ortner <boh@zurich.ibm.com>
Co-authored-by: Cyrus Leung <cyrus.tl.leung@gmail.com>
Co-authored-by: Tyler Michael Smith <tysmith@redhat.com>
2025-05-06 12:00:31 +08:00
5941e0b7ea
[TPU][V1] Add support for top-logprobs ( #17072 )
...
Signed-off-by: NickLucche <nlucches@redhat.com>
2025-05-05 14:20:15 -07:00
9765940824
[TPU] Enable gemma3-27b with TP>1 on multi-chips. ( #17335 )
...
Signed-off-by: Xiongfei Wei <isaacwxf23@gmail.com>
2025-05-05 14:19:58 -07:00
5ea5c514da
[BugFix] Increase timeout for startup failure test ( #17642 )
...
Signed-off-by: Nick Hill <nhill@redhat.com>
2025-05-05 20:53:19 +00:00
1d0c9d6b2d
[Kernel] some optimizations for dense marlin and moe marlin ( #16850 )
...
Signed-off-by: Jinzhen Lin <linjinzhen@hotmail.com>
2025-05-05 09:39:30 -07:00
d6484ef3c3
Add full API docs and improve the UX of navigating them ( #17485 )
...
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
2025-05-03 19:42:43 -07:00
f66f1e0fa3
[Bugfix] Fix broken Qwen2.5-omni tests ( #17613 )
...
Signed-off-by: Isotr0py <2037008807@qq.com>
2025-05-03 17:08:14 +00:00
887d7af882
[Core] Gate `prompt_embeds` behind a feature flag ( #17607 )
...
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
2025-05-04 00:19:20 +08:00
b90b0852e9
[easy] Print number of needed GPUs in skip message ( #17594 )
...
Signed-off-by: rzou <zou3519@gmail.com>
2025-05-02 15:27:43 -07:00
3e887d2e0c
permute/unpermute kernel for moe optimization ( #14568 )
...
Signed-off-by: Caleb_Du <Caleb_Du@zju.edu.cn>
2025-05-02 11:31:55 -07:00
cb234955df
[Misc] Clean up input processing ( #17582 )
...
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
2025-05-02 08:11:53 -07:00
99404f53c7
[Security] Fix image hash collision ( #17378 )
...
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
2025-05-02 08:36:39 -04:00
785d75a03b
Automatically tell users that dict args must be valid JSON in CLI ( #17577 )
...
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
2025-05-02 05:24:55 -07:00
d7543862bd
[Misc] Rename assets for testing ( #17575 )
...
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
2025-05-02 03:29:25 -07:00
c777df79f7
[BugFix] Fix Memory Leak ( #17567 )
...
Signed-off-by: rshaw@neuralmagic.com <robertgshaw2@gmail.com>
2025-05-02 01:07:03 -07:00
cc2a77d7f1
[Core] [Bugfix] Add Input Embeddings ( #15428 )
...
Signed-off-by: Andrew Sansom <andrew@protopia.ai>
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
Co-authored-by: 临景 <linjing.yx@alibaba-inc.com>
Co-authored-by: Bryce1010 <bryceyx@gmail.com>
Co-authored-by: Nan2018 <nan@protopia.ai>
Co-authored-by: Cyrus Leung <cyrus.tl.leung@gmail.com>
Co-authored-by: DarkLight1337 <tlleungac@connect.ust.hk>
2025-05-02 01:06:39 -07:00
109e15a335
Add `pt_load_map_location` to allow loading to cuda ( #16869 )
...
Signed-off-by: Jerry Zhang <jerryzh168@gmail.com>
2025-05-01 23:23:42 -07:00
f89d0e11bf
[Misc] Continue refactoring model tests ( #17573 )
...
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
2025-05-01 22:06:08 -07:00
292fc59d61
[CI] Actually run tests/kv_transfer/test_disagg.py in CI ( #17555 )
...
Signed-off-by: mgoin <mgoin64@gmail.com>
2025-05-02 04:05:04 +00:00
88c8304104
[Model] Refactor Ovis2 to support original tokenizer ( #17537 )
...
Signed-off-by: Isotr0py <2037008807@qq.com>
2025-05-01 11:00:53 -07:00
460a2b1100
[torch.compile] Add torch inductor pass for fusing silu_and_mul with subsequent scaled_fp8_quant operations ( #10867 )
...
Signed-off-by: Sage Moore <sage@neuralmagic.com>
2025-05-01 07:59:28 -07:00
98060b001d
[Feature][Frontend]: Deprecate --enable-reasoning ( #17452 )
...
Signed-off-by: chaunceyjiang <chaunceyjiang@gmail.com>
2025-05-01 06:46:16 -07:00
b74d888c63
Fix more broken speculative decode tests ( #17450 )
...
Signed-off-by: Huy Do <huydhn@gmail.com>
2025-05-01 06:05:58 -07:00
48e925fab5
[Misc] Clean up test docstrings and names ( #17521 )
...
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
2025-05-01 05:19:32 -07:00
fbefc8a78d
[Core] Enable IPv6 with vllm.utils.make_zmq_socket() ( #16506 )
...
Signed-off-by: Russell Bryant <rbryant@redhat.com>
2025-05-01 09:38:18 +00:00
13cf6b6236
[BugFix] fix speculative decoding memory leak when speculation is disabled ( #15506 )
...
Signed-off-by: Noah Yoshida <noahcy117@gmail.com>
2025-04-30 23:28:17 -07:00
afb4429b4f
[CI/Build] Reorganize models tests ( #17459 )
...
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
2025-04-30 23:03:08 -07:00
aa4502e7f3
[CI][Bugfix] Fix failing V1 Test due to missing 'cache_salt' arg ( #17500 )
...
Signed-off-by: mgoin <mgoin64@gmail.com>
2025-04-30 21:03:30 -07:00
17b4d85f63
[CI][TPU] Skip structured outputs+spec decode tests on TPU ( #17510 )
...
Signed-off-by: mgoin <mgoin64@gmail.com>
2025-04-30 20:36:20 -07:00
dbc18e7816
[CI][TPU] Skip Multimodal test ( #17488 )
...
Signed-off-by: Siyuan Liu <lsiyuan@google.com>
2025-04-30 19:51:39 -07:00
81ecf425f0
[v1][Spec Decode] Make sliding window compatible with eagle prefix caching ( #17398 )
...
Signed-off-by: Chen Zhang <zhangch99@outlook.com>
2025-04-30 18:25:53 +00:00
947f2f5375
[V1] Allow turning off pickle fallback in vllm.v1.serial_utils ( #17427 )
...
Signed-off-by: Russell Bryant <rbryant@redhat.com>
Co-authored-by: Cyrus Leung <cyrus.tl.leung@gmail.com>
2025-04-30 16:10:54 +00:00
0be6d05b5e
[V1][Metrics] add support for kv event publishing ( #16750 )
...
Signed-off-by: alec-flowers <aflowers@nvidia.com>
Signed-off-by: Mark McLoughlin <markmc@redhat.com>
Co-authored-by: Mark McLoughlin <markmc@redhat.com>
2025-04-30 07:44:45 -07:00
77073c77bc
[Core] Prevent side-channel attacks via cache salting ( #17045 )
...
Signed-off-by: Marko Rosenmueller <5467316+dr75@users.noreply.github.com>
2025-04-30 20:27:21 +08:00
a7d5b016bd
[TPU][V1][CI] Update regression test baseline for v6 CI ( #17064 )
...
Signed-off-by: NickLucche <nlucches@redhat.com>
2025-04-30 04:03:22 -07:00
54072f315f
[MODEL ADDITION] Ovis2 Model Addition ( #15826 )
...
Signed-off-by: Marco <121761685+mlinmg@users.noreply.github.com>
Signed-off-by: Isotr0py <2037008807@qq.com>
Signed-off-by: isotr0py <2037008807@qq.com>
Co-authored-by: Isotr0py <2037008807@qq.com>
Co-authored-by: Isotr0py <mozf@mail2.sysu.edu.cn>
2025-04-30 07:33:29 +00:00
88fcf00dda
Fix some speculative decode tests with tl.dot ( #17371 )
...
Signed-off-by: Huy Do <huydhn@gmail.com>
2025-04-29 19:41:02 -07:00
13698db634
Improve configs - `ModelConfig` ( #17130 )
...
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
2025-04-30 10:38:22 +08:00
1c2bc7ead0
Truncation control for embedding models ( #14776 )
...
Signed-off-by: Gabriel Marinho <gmarinho@ibm.com>
Signed-off-by: Max de Bayser <mbayser@br.ibm.com>
Co-authored-by: Max de Bayser <mbayser@br.ibm.com>
2025-04-30 09:24:57 +08:00
34120f5acd
[V1][Feature] Enable Speculative Decoding with Structured Outputs ( #14702 )
...
Signed-off-by: Benjamin Chislett <benjamin.chislett@centml.ai>
Signed-off-by: Benjamin Chislett <chislett.ben@gmail.com>
2025-04-30 00:02:10 +00:00
7489ec0bab
Remove Bamba 9B from CI ( #17407 )
...
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
2025-04-29 21:10:31 +00:00
0350809f3a
Remove Falcon3 2x7B from CI ( #17404 )
...
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
2025-04-29 19:52:25 +00:00
a6977dbd15
Simplify (and fix) passing of guided decoding backend options ( #17008 )
...
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
2025-04-29 19:02:23 +00:00
a39203f99e
[Bugfix] add qwen3 reasoning-parser fix content is None when disable … ( #17369 )
...
Signed-off-by: mofanke <mofanke@gmail.com>
2025-04-29 16:32:40 +00:00
2ef5d106bb
Improve literal dataclass field conversion to argparse argument ( #17391 )
...
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
2025-04-29 16:25:08 +00:00
88ad9ec6b2
[Frontend] Support `chat_template_kwargs` in `LLM.chat` ( #17356 )
...
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
2025-04-29 22:03:35 +08:00
00ee37efa2
[Bugfix] Clean up MiniMax-VL and fix processing ( #17354 )
...
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
2025-04-29 20:42:16 +08:00
890f104cdf
[Doc] Fix QWen3MOE info ( #17381 )
...
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
2025-04-29 12:38:32 +00:00
bdb2cddafc
[Misc]Use a platform independent interface to obtain the device attributes ( #17100 )
2025-04-29 06:59:13 +00:00
cde384cd92
[Model] support MiniMax-VL-01 model ( #16328 )
...
Signed-off-by: qingjun <qingjun@minimaxi.com>
2025-04-29 12:05:50 +08:00
86d9fc29cb
implement Structural Tag with Guidance backend ( #17333 )
...
Signed-off-by: Michal Moskal <michal@moskal.me>
2025-04-29 02:21:32 +00:00
b6dd32aa07
Make name of `compressed-tensors` quant method consistent across vLLM ( #17255 )
...
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
2025-04-28 16:28:13 +00:00
f94886946e
Improve conversion from dataclass configs to argparse arguments ( #17303 )
...
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
2025-04-28 16:22:12 +00:00
fa93cd9f60
[Model] Add Granite Speech Support ( #16246 )
...
Signed-off-by: Alex-Brooks <Alex.brooks@ibm.com>
Signed-off-by: Alex-Brooks <Alex.Brooks@ibm.com>
2025-04-28 10:05:00 +00:00
20e489eaa1
[V1][Spec Decode] Make eagle compatible with prefix caching. ( #17137 )
...
Signed-off-by: LiuXiaoxuanPKU <lilyliupku@gmail.com>
2025-04-27 09:29:43 -07:00
690fe019f0
[Feature] support sequence parallelism using compilation pass ( #16155 )
...
Signed-off-by: cascade812 <cascade812@outlook.com>
Signed-off-by: Tyler Michael Smith <tyler@neuralmagic.com>
Co-authored-by: Tyler Michael Smith <tyler@neuralmagic.com>
2025-04-27 06:29:35 -07:00
ed7a29d9f8
[NVIDIA] Support Cutlass MLA for Blackwell GPUs ( #16032 )
...
Signed-off-by: kaixih <kaixih@nvidia.com>
2025-04-27 06:29:21 -07:00
756848e79e
[Bugfix] Fix Lora Name Parsing ( #17196 )
...
Signed-off-by: Alex-Brooks <Alex.Brooks@ibm.com>
Co-authored-by: Jee Jee Li <pandaleefree@gmail.com>
2025-04-27 20:33:09 +08:00
93a126fbc7
[Misc] Make cached tokenizer pickle-compatible ( #17048 )
...
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
2025-04-27 13:05:00 +08:00
8e4b351a0c
[Kernel][Triton][FP8] Adding fp8 and variable length sequence support to Triton FAv2 kernel ( #12591 )
...
Signed-off-by: Randall Smith <Randall.Smith@amd.com>
2025-04-27 00:35:08 +00:00
9869453c42
Update test_flash_attn.py ( #17102 )
...
Signed-off-by: ShuaibinLi <lishuaibin@live.cn>
2025-04-26 22:17:35 +00:00
fd11a325b8
[MISC] rename interval to max_recent_requests ( #14285 )
2025-04-26 16:59:18 +00:00
f8acd01ff7
[V1] Add `structural_tag` support using xgrammar ( #17085 )
2025-04-26 14:06:37 +00:00
909fdaf152
[Bugfix] Fix standard models tests ( #17217 )
...
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
2025-04-26 02:26:41 -07:00
df6f3ce883
[Core] Remove prompt string from engine core data structures ( #17214 )
...
Signed-off-by: Nick Hill <nhill@redhat.com>
2025-04-25 23:41:05 -07:00
513f074766
[CI/test] Fix Eagle Correctness Test ( #17209 )
...
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
2025-04-25 23:40:36 -07:00
b07bf83c7d
[BugFix] Avoid race conditions in zero-copy tensor transmission ( #17203 )
...
Signed-off-by: Nick Hill <nhill@redhat.com>
2025-04-26 06:00:07 +00:00
53e8cf53a4
[V1][Metrics] Allow V1 AsyncLLM to use custom logger ( #14661 )
...
Signed-off-by: Zijing Liu <liuzijing2014@gmail.com>
Signed-off-by: Mark McLoughlin <markmc@redhat.com>
Signed-off-by: Nick Hill <nhill@redhat.com>
Co-authored-by: Mark McLoughlin <markmc@redhat.com>
Co-authored-by: Nick Hill <nhill@redhat.com>
2025-04-25 22:05:40 -07:00
9e96f56efb
Allocate kv_cache with stride order ( #16605 )
...
Signed-off-by: shuw <shuw@nvidia.com>
2025-04-25 22:03:31 -07:00
a0e619e62a
[V1][Spec Decode] EAGLE-3 Support ( #16937 )
...
Signed-off-by: Bryan Lu <yuzhelu@amazon.com>
Signed-off-by: Benjamin Chislett <benjamin.chislett@centml.ai>
Co-authored-by: Bryan Lu <yuzhelu@amazon.com>
2025-04-25 15:43:07 -07:00
70116459c3
[BugFix][Frontend] Fix `LLM.chat()` tokenization ( #16081 )
...
Signed-off-by: Nick Hill <nhill@redhat.com>
2025-04-25 22:20:05 +00:00
43faa0461a
[Bugfix] Fix hybrid model tests ( #17182 )
...
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
2025-04-25 15:14:37 -07:00
423e9f1cbe
Use Transformers helper `get_text_config()` instead of checking for `text_config` ( #17105 )
...
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
2025-04-25 08:47:35 -07:00
0bd7f8fca5
Bump Transformers to 4.51.3 ( #17116 )
...
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
2025-04-25 08:34:34 -07:00
19dcc02a72
[Bugfix] Fix mistral model tests ( #17181 )
...
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
2025-04-25 06:03:34 -07:00
6aae216b4e
[Bugfix] remove fallback in guided_json (int range, patterns) ( #16725 )
...
Signed-off-by: csy1204 <josang1204@gmail.com>
Co-authored-by: 조상연[플레이스 AI] <sang-yeon.cho@navercorp.com>
2025-04-25 06:54:43 +00:00
eef364723c
[FEAT] [ROCm]: AITER Fused MOE V1 Support ( #16752 )
...
Signed-off-by: vllmellm <vllm.ellm@embeddedllm.com>
Co-authored-by: tjtanaa <tunjian.tan@embeddedllm.com>
2025-04-25 11:06:50 +08:00
05e1fbfc52
Add chat template for Llama 4 models ( #16428 )
...
Signed-off-by: Max de Bayser <mbayser@br.ibm.com>
2025-04-24 20:19:36 +00:00
0fa939e2d1
Improve configs - `LoRAConfig` + `PromptAdapterConfig` ( #16980 )
...
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
2025-04-24 10:29:34 -07:00
340d7b1b21
[V1][Spec Decoding] Add num_drafts and num_accepted_tokens_per_position metrics ( #16665 )
...
Signed-off-by: Mark McLoughlin <markmc@redhat.com>
2025-04-24 08:57:40 -07:00
82e43b2d7e
Add missing rocm_skinny_gemms kernel test to CI ( #17060 )
...
Signed-off-by: mgoin <mgoin64@gmail.com>
2025-04-24 07:49:37 -07:00
67309a1cb5
[Frontend] Using matryoshka_dimensions control the allowed output dimensions. ( #16970 )
2025-04-24 07:06:28 -07:00
c0dfd97519
[V1][PP] Optimization: continue scheduling prefill chunks ( #17080 )
...
Signed-off-by: Rui Qiao <ruisearch42@gmail.com>
2025-04-24 05:27:08 -07:00
a9138e85b1
Fix OOT registration test ( #17099 )
...
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
2025-04-24 04:44:12 -07:00
0a05ed57e6
Simplify `TokenizerGroup` ( #16790 )
...
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
2025-04-24 04:43:56 -07:00
14288d1332
Disable enforce_eager for V1 TPU sampler and structured output tests ( #17016 )
...
Signed-off-by: mgoin <mgoin64@gmail.com>
2025-04-24 02:50:09 -07:00
b411418ff0
[Chore] Remove Sampler from Model Code ( #17084 )
...
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
2025-04-24 02:49:33 -07:00
3cde34a4a4
[Frontend] Support guidance:no-additional-properties for compatibility with xgrammar ( #15949 )
...
Signed-off-by: Travis Johnson <tsjohnso@us.ibm.com>
2025-04-23 18:34:41 +00:00
6317a5174a
Categorize `tests/kernels/` based on kernel type ( #16799 )
...
Signed-off-by: mgoin <mgoin64@gmail.com>
2025-04-23 09:21:07 -04:00
1e013fa388
[V1][DP] More robust DP/EP dummy request coordination ( #16277 )
...
Signed-off-by: Nick Hill <nhill@redhat.com>
2025-04-22 19:12:15 -07:00
bc7c4d206b
[Kernel][ROCM] Upstream prefix prefill speed up for vLLM V1 ( #13305 )
...
Signed-off-by: Sage Moore <sage@neuralmagic.com>
Signed-off-by: root <root@banff-cyxtera-s73-5.ctr.dcgpu>
Signed-off-by: Aleksandr Malyshev <maleksan@amd.com>
Signed-off-by: root <root@banff-cyxtera-s65-4.amd.com>
Signed-off-by: maleksan85 <maleksan@amd.com>
Signed-off-by: <>
Co-authored-by: Sage Moore <sage@neuralmagic.com>
Co-authored-by: root <root@banff-cyxtera-s73-5.ctr.dcgpu>
Co-authored-by: Aleksandr Malyshev <maleksan@amd.com>
Co-authored-by: qli88 <qiang.li2@amd.com>
Co-authored-by: root <root@banff-cyxtera-s65-4.amd.com>
2025-04-22 19:11:56 -07:00
36fe78769f
[Bugfix] validate urls object for multimodal content parts ( #16990 )
...
Signed-off-by: Guillaume Calmettes <gcalmettes@scaleway.com>
2025-04-23 09:43:06 +08:00
83d933718c
[Core][V1][TPU] Enable structured decoding on TPU V1 ( #16499 )
...
Signed-off-by: Chenyaaang <chenyangli@google.com>
2025-04-22 18:05:23 -06:00
30bc3e0f66
[FEAT][ROCm]: Support AITER MLA ( #15893 )
...
Signed-off-by: vllmellm <vllm.ellm@embeddedllm.com>
Co-authored-by: qli88 <qiang.li2@amd.com>
2025-04-22 09:31:13 -07:00
8d32dc603d
[Kernel] Support Microsoft Runtime Kernel Lib for our Low Precision Computation - BitBLAS ( #6036 )
...
Signed-off-by: xinyuxiao <xinyuxiao2024@gmail.com>
Co-authored-by: xinyuxiao <xinyuxiao2024@gmail.com>
2025-04-22 09:01:36 +01:00
c4ab9f3e71
[V1] Remove pre-allocation for KV cache ( #16941 )
...
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
2025-04-22 00:52:18 -07:00
acba33a0f1
[Bugfix] Fix the issue where llm.generate cannot be called repeatedly after setting GuidedDecodingParams ( #16767 )
...
Signed-off-by: chaunceyjiang <chaunceyjiang@gmail.com>
Signed-off-by: Russell Bryant <rbryant@redhat.com>
Co-authored-by: Russell Bryant <rbryant@redhat.com>
2025-04-22 06:02:20 +00:00
188b7f9b8c
[Performance][ROCm] Add skinny gemms for unquantized linear on ROCm ( #15830 )
...
Signed-off-by: charlifu <charlifu@amd.com>
Co-authored-by: Tyler Michael Smith <tysmith@redhat.com>
2025-04-21 20:46:22 -07:00
7b8a2ab76f
[Kernel] Add expert_map support to Cutlass FP8 MOE ( #16861 )
...
Signed-off-by: varun sundar rabindranath <vsundarr@redhat.com>
Co-authored-by: varun sundar rabindranath <vsundarr@redhat.com>
2025-04-21 20:44:32 -07:00
0e4254492f
[Bugfix]: fix issue with n>1 sampling on v1 requests overriding each other ( #16863 )
...
Signed-off-by: Jeffrey Li <jeffrey.dot.li@gmail.com>
2025-04-22 11:40:19 +08:00
fa3bba2a53
[TPU][V1] Enable Top-P ( #16843 )
...
Signed-off-by: NickLucche <nlucches@redhat.com>
Co-authored-by: mgoin <mgoin64@gmail.com>
2025-04-22 00:46:07 +00:00
986537f1c3
[V1] V1 FlashInfer Attention ( #16684 )
...
Signed-off-by: mgoin <mgoin64@gmail.com>
Co-authored-by: Aurick Qiao <qiao@aurick.net>
2025-04-22 00:38:41 +00:00
210207525e
[TPU][V1] Capture multimodal encoder during model compilation ( #15051 )
...
Signed-off-by: Michael Goin <mgoin64@gmail.com>
Signed-off-by: NickLucche <nlucches@redhat.com>
Co-authored-by: Michael Goin <mgoin64@gmail.com>
Co-authored-by: Siyuan Liu <lsiyuan@google.com>
2025-04-21 18:36:59 -06:00
471fe65630
[TPU][V1] Implicitly adjust page size when there's SMEM OOM ( #16871 )
...
Signed-off-by: Chengji Yao <chengjiyao@google.com>
2025-04-21 15:43:13 -06:00
3a0fba5cf4
[V1][Spec Decode] Handle draft tokens beyond max_model_len ( #16087 )
...
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
2025-04-21 12:38:50 -07:00
bb3605db85
[Bugfix] Fix v1/spec_decode/test_ngram.py ( #16895 )
...
Signed-off-by: qizixi <qizixi@meta.com>
2025-04-20 20:54:29 -07:00
87aaadef73
Serialize tensors using int8 views ( #16866 )
...
Signed-off-by: Staszek Pasko <staszek@gmail.com>
Co-authored-by: Nick Hill <nhill@redhat.com>
2025-04-19 10:28:34 -07:00
83f3c3bd91
[Model] Refactor Phi-4-multimodal to use merged processor and support V1 ( #15477 )
...
Signed-off-by: Isotr0py <2037008807@qq.com>
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
Co-authored-by: DarkLight1337 <tlleungac@connect.ust.hk>
2025-04-19 02:26:11 -07:00
d9737ca1c6
[V1][Misc] stop update prefix cache stats when logs_stats is disabled ( #16460 )
...
Signed-off-by: vie-serendipity <2733147505@qq.com>
2025-04-19 02:25:19 -07:00
9d4ca19d50
[Misc] Benchmarks for audio models ( #16505 )
...
Signed-off-by: NickLucche <nlucches@redhat.com>
2025-04-19 02:24:14 -07:00
2ef0dc53b8
[Frontend] Add sampling params to `v1/audio/transcriptions` endpoint ( #16591 )
...
Signed-off-by: Jannis Schönleber <joennlae@gmail.com>
Signed-off-by: NickLucche <nlucches@redhat.com>
Co-authored-by: Jannis Schönleber <joennlae@gmail.com>
2025-04-19 07:03:54 +00:00
2c1bd848a6
[Model][VLM] Add Qwen2.5-Omni model support (thinker only) ( #15130 )
...
Signed-off-by: fyabc <suyang.fy@alibaba-inc.com>
Signed-off-by: Roger Wang <ywang@roblox.com>
Co-authored-by: Roger Wang <136131678+ywang96@users.noreply.github.com>
Co-authored-by: Roger Wang <ywang@roblox.com>
Co-authored-by: Xiong Wang <wangxiongts@163.com>
2025-04-18 23:14:36 -07:00
3d3ab3689f
[New Model]: Snowflake Arctic Embed (Family) ( #16649 )
2025-04-18 08:11:57 -07:00
686623c5e7
Fix `nullable_kvs` fallback ( #16837 )
...
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
2025-04-18 05:58:39 -07:00
e78587a64c
Improve-mm-and-pooler-and-decoding-configs ( #16789 )
...
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
2025-04-17 22:13:32 -07:00
c16fb5dae8
[Doc] Improve help examples for `--compilation-config` ( #16729 )
...
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
2025-04-17 21:22:34 -07:00
e37073efd7
Add property-based testing for vLLM endpoints using an API defined by an OpenAPI 3.1 schema ( #16721 )
...
Signed-off-by: Tarun Kumar <takumar@redhat.com>
Signed-off-by: Nick Hill <nhill@redhat.com>
Co-authored-by: Nick Hill <nhill@redhat.com>
2025-04-17 21:08:27 -07:00
3408e47159
[P/D][V1] KV Connector API V1 ( #15960 )
...
Signed-off-by: ApostaC <yihua98@uchicago.edu>
Signed-off-by: rshaw@neuralmagic.com <robertgshaw2@gmail.com>
Signed-off-by: remi <remi@mistral.ai>
Co-authored-by: rshaw@neuralmagic.com <robertgshaw2@gmail.com>
Co-authored-by: Robert Shaw <114415538+robertgshaw2-redhat@users.noreply.github.com>
Co-authored-by: Rémi Delacourt <54138269+Flechman@users.noreply.github.com>
Co-authored-by: Tyler Michael Smith <tysmith@redhat.com>
2025-04-17 13:22:40 -07:00
eb5819b2d9
[V1][TPU] Enable Top K ( #15489 )
...
Signed-off-by: NickLucche <nlucches@redhat.com>
Signed-off-by: Hyesoo Yang <hyeygit@gmail.com>
Co-authored-by: Hyesoo Yang <hyeygit@gmail.com>
2025-04-17 18:18:11 +00:00
5989f4684d
[TPU][V1] Fix padding recompilation when `max-num-batched-tokens` is not even ( #16726 )
...
Signed-off-by: NickLucche <nlucches@redhat.com>
2025-04-17 18:09:57 +00:00
05fcd1b430
[V1][Perf] Faster incremental detokenization ( #15137 )
...
Signed-off-by: Nick Hill <nhill@redhat.com>
2025-04-17 07:45:24 -07:00
d27ea94034
Improve configs - `TokenizerPoolConfig` + `DeviceConfig` ( #16603 )
...
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
2025-04-17 11:19:42 +00:00
5b1aca2ae3
[Bugfix] Fix GLM4 model ( #16618 )
...
Signed-off-by: intervitens <intervitens@tutanota.com>
2025-04-17 03:35:07 -07:00
cb072ce93b
[Bugfix] Update Florence-2 tokenizer to make grounding tasks work ( #16734 )
...
Signed-off-by: Isotr0py <2037008807@qq.com>
2025-04-17 04:17:39 +00:00
2b05b8ce69
[V1][Frontend] Improve Shutdown And Logs ( #11737 )
...
Signed-off-by: rshaw@neuralmagic.com <rshaw@neuralmagic.com>
Signed-off-by: Andrew Feldman <afeldman@neuralmagic.com>
Signed-off-by: Nick Hill <nhill@redhat.com>
Co-authored-by: rshaw@neuralmagic.com <rshaw@neuralmagic.com>
Co-authored-by: Cyrus Leung <cyrus.tl.leung@gmail.com>
Co-authored-by: Russell Bryant <rbryant@redhat.com>
Co-authored-by: Andrew Feldman <afeldman@neuralmagic.com>
Co-authored-by: afeldman-nm <156691304+afeldman-nm@users.noreply.github.com>
Co-authored-by: Nick Hill <nhill@redhat.com>
2025-04-16 19:48:34 -07:00
3092375e27
[V1][Performance] Implement custom serializaton for MultiModalKwargs [Rebased] ( #16432 )
...
Signed-off-by: Staszek Pasko <staszek@gmail.com>
Signed-off-by: Nick Hill <nhill@redhat.com>
Co-authored-by: Cyrus Leung <cyrus.tl.leung@gmail.com>
Co-authored-by: Nick Hill <nhill@redhat.com>
2025-04-16 19:28:32 -07:00
ee378f3d49
[Model] support modernbert ( #16648 )
...
Signed-off-by: 唯勤 <xsank.mz@alibaba-inc.com>
Co-authored-by: 唯勤 <xsank.mz@alibaba-inc.com>
2025-04-16 05:30:15 -07:00
976711d9db
[V1][Structured Output] Move xgrammar related utils to `backend_xgrammar.py` ( #16578 )
...
Signed-off-by: shen-shanshan <467638484@qq.com>
2025-04-16 17:01:36 +08:00
3badb0213b
[Model] Add PLaMo2 ( #14323 )
...
Signed-off-by: Shinichi Hemmi <50256998+Alnusjaponica@users.noreply.github.com>
Signed-off-by: shemmi <shemmi@preferred.jp>
Co-authored-by: Kento Nozawa <nzw0301@preferred.jp>
Co-authored-by: Hiroaki Mikami <mhiroaki@preferred.jp>
Co-authored-by: Calvin Metzger <metzger@preferred.jp>
2025-04-15 19:31:30 -07:00
fdcb850f14
[Misc] Enable vLLM to Dynamically Load LoRA from a Remote Server ( #10546 )
...
Signed-off-by: Angky William <angkywilliam@Angkys-MacBook-Pro.local>
Co-authored-by: Angky William <angkywilliam@Angkys-MacBook-Pro.local>
2025-04-15 22:31:38 +00:00
54a66e5fee
[Misc] Update `compressed-tensors` WNA16 to support zero-points ( #14211 )
2025-04-15 07:33:51 -06:00
1575c1701a
[CI/Build] Fix LoRA OOM ( #16624 )
...
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
2025-04-15 16:38:19 +08:00
b4fe16c75b
Add `vllm bench [latency, throughput]` CLI commands ( #16508 )
...
Signed-off-by: mgoin <mgoin64@gmail.com>
2025-04-14 23:10:35 -07:00
bc5dd4f669
[Bugfix] Fix broken GritLM model and tests (missing pooling_metadata) ( #16631 )
...
Signed-off-by: Pooya Davoodi <pooya.davoodi@parasail.io>
2025-04-14 23:09:58 -07:00
dbb036cf61
[Bugfix] Fix tests/kernels/test_mamba_ssm_ssd.py ( #16623 )
...
Signed-off-by: Tyler Michael Smith <tyler@neuralmagic.com>
2025-04-15 05:35:38 +00:00
d06ba4ed3f
[Kernel] moe wna16 marlin kernel ( #14447 )
...
Signed-off-by: Jinzhen Lin <linjinzhen@hotmail.com>
Co-authored-by: Michael Goin <michael@neuralmagic.com>
Co-authored-by: mgoin <mgoin64@gmail.com>
2025-04-14 20:05:22 -07:00
6b40996ae8
[Core][Bugfix] Fix Offline MM Beam Search ( #16390 )
...
Signed-off-by: Alex-Brooks <Alex.Brooks@ibm.com>
Co-authored-by: Cyrus Leung <cyrus.tl.leung@gmail.com>
2025-04-15 10:33:02 +08:00
b1308b84a3
[Model][VLM] Add Kimi-VL model support ( #16387 )
...
Signed-off-by: courage17340 <courage17340@163.com>
2025-04-14 21:41:48 +00:00
b3f2fddd17
[TPU][V1] Fix exponential padding when `max-num-batched-tokens` is not a power of 2 ( #16596 )
...
Signed-off-by: NickLucche <nlucches@redhat.com>
2025-04-14 17:01:05 +00:00
aa29841ede
[Bugfix] Multi-modal caches not acting like LRU caches ( #16593 )
...
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
2025-04-14 09:24:16 -07:00
dc1b4a6f13
[Core][V0] Enable regex support with xgrammar ( #13228 )
...
Signed-off-by: Russell Bryant <rbryant@redhat.com>
2025-04-14 10:13:38 +08:00
f49e5aff11
[V1][Spec Decode] KV cache slots for eagle heads ( #16370 )
...
Signed-off-by: LiuXiaoxuanPKU <lilyliupku@gmail.com>
2025-04-12 19:42:51 -07:00
6c11ecf8d3
[Bugfix] Validate logit biases to prevent out of vocab ids crashing engine ( #16529 )
...
Signed-off-by: Ryan McConville <ryan@ryanmcconville.com>
2025-04-12 20:19:19 +00:00
d9fc8cd9da
[V1] Enable multi-input by default ( #15799 )
...
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
2025-04-12 08:52:39 +00:00
c5bc0e7fcc
[Misc] Update chat utils tests ( #16520 )
...
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
2025-04-12 06:48:43 +00:00
fbf722c6e6
[Frontend] support matryoshka representation / support embedding API dimensions ( #16331 )
2025-04-11 23:23:10 -07:00
e92d7085bf
[Feature][V1] Add xgrammar to support minLength, maxLength with test ( #16516 )
...
Signed-off-by: Leon Seidel <leon.seidel@fau.de>
2025-04-11 23:22:07 -07:00
41cc883c29
[BugFix] Handle non-contiguous tensors properly when serializing ( #16492 )
...
Signed-off-by: Nick Hill <nhill@redhat.com>
2025-04-11 17:54:06 -07:00
16eda8c43a
[Frontend] Added chat templates for LLaMa4 pythonic tool calling ( #16463 )
...
Signed-off-by: Ye (Charlotte) Qi <yeq@meta.com>
Co-authored-by: Kai Wu <kaiwu@meta.com>
2025-04-12 06:26:17 +08:00
71b9cde010
[Bugfix] handle alignment of encoder_seq_lens in mllama.py ( #14784 )
...
Signed-off-by: Travis Johnson <tsjohnso@us.ibm.com>
2025-04-11 19:59:50 +00:00
f41647ee6b
[Kernel] Support W8A8 channel-wise weights and per-token activations in triton fused_moe_kernel ( #16366 )
...
Signed-off-by: mgoin <mgoin64@gmail.com>
2025-04-11 17:54:08 +00:00
9e90c9f73f
[Bugfix] Fix bugs of running Quark quantized models ( #16236 )
...
Signed-off-by: chaow <chaow@amd.com>
2025-04-11 10:18:32 -04:00
e9528f6dc6
[Kernel] support merge_attn_states CUDA kernel, 3x speedup ( #16173 )
...
Signed-off-by: DefTruth <qiustudent_r@163.com>
2025-04-11 06:50:50 -06:00
aa3b3d76e0
Enforce valid max_num_batched_tokens when disable_chunked_mm_input=True ( #16447 )
...
Signed-off-by: mgoin <mgoin64@gmail.com>
2025-04-11 08:09:52 +00:00
93195146ea
[Bugfix][VLM] Fix failing Phi-4-MM multi-images tests and add vision-speech test ( #16424 )
...
Signed-off-by: Isotr0py <2037008807@qq.com>
2025-04-11 04:57:16 +00:00
3cc9af88ff
[TPU][V1] Disable per-request seed/Generator ( #16172 )
...
Signed-off-by: NickLucche <nlucches@redhat.com>
2025-04-10 17:05:44 -04:00
dd143ef541
[V1] Zero-copy tensor/ndarray serialization/transmission ( #13790 )
...
Signed-off-by: Nick Hill <nhill@redhat.com>
2025-04-10 19:23:14 +00:00
e8224f3dca
[V1][Spec Decode] Eagle Model loading ( #16035 )
...
Signed-off-by: LiuXiaoxuanPKU <lilyliupku@gmail.com>
2025-04-10 11:21:48 -07:00
9665313c39
[V1] Set structured output backend to `auto` by default ( #15724 )
...
Signed-off-by: Russell Bryant <rbryant@redhat.com>
2025-04-10 17:53:26 +00:00
83b824c8b4
[VLM] Remove `BaseProcessingInfo.get_mm_max_tokens_per_item` ( #16408 )
...
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
2025-04-10 09:06:58 -07:00
3d4c87758e
[Misc] Update transformers version limits of multi-modal tests ( #16381 )
...
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
2025-04-09 23:03:33 -07:00
1e44ffc3ff
Add GLM-4-0414 support ( #16338 )
...
Signed-off-by: lvfei.lv <lvfei.lv@alibaba-inc.com>
Signed-off-by: zRzRzRzRzRzRzR <2448370773@qq.com>
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
Signed-off-by: yihong0618 <zouzou0208@gmail.com>
Signed-off-by: Lu Fang <fanglu@fb.com>
Signed-off-by: Ajay Vohra <ajayvohr@amazon.com>
Signed-off-by: NickLucche <nlucches@redhat.com>
Signed-off-by: Guillaume Calmettes <gcalmettes@scaleway.com>
Co-authored-by: Accelerator1996 <lvfei.lv@alibaba-inc.com>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>
Co-authored-by: Michael Goin <michael@neuralmagic.com>
Co-authored-by: yihong <zouzou0208@gmail.com>
Co-authored-by: Lucia Fang <116399278+luccafong@users.noreply.github.com>
Co-authored-by: ajayvohra2005 <ajayvohr@amazon.com>
Co-authored-by: Nicolò Lucchesi <nlucches@redhat.com>
Co-authored-by: Guillaume Calmettes <gcalmettes@scaleway.com>
2025-04-10 09:19:42 +08:00
a454748544
[TPU][V1] Refine tpu_model_runner to mitigate future recompilation issues ( #16275 )
...
Signed-off-by: Chengji Yao <chengjiyao@google.com>
2025-04-09 18:51:51 -06:00
98d01d3ce2
[Bugfix][Frontend] respect provided default guided decoding backend ( #15476 )
...
Signed-off-by: Guillaume Calmettes <gcalmettes@scaleway.com>
2025-04-09 05:11:10 -07:00
24f6b9a713
[Misc] Fix test_sharded_state_loader.py( #16004 ) ( #16005 )
...
Signed-off-by: lvfei.lv <lvfei.lv@alibaba-inc.com>
2025-04-09 14:47:30 +08:00
9cdde47289
[BugFix] Fix fusion test and add them to CI ( #16287 )
...
Signed-off-by: luka <luka@neuralmagic.com>
2025-04-08 23:46:45 -07:00
b1eb4ca152
[TPU] Update PyTorch/XLA ( #16288 )
...
Signed-off-by: Chengji Yao <chengjiyao@google.com>
2025-04-09 14:46:32 +08:00
87b4ac56c2
[CI][Bugfix] Fix bad tolerance for test_batch_base64_embedding ( #16221 )
...
Signed-off-by: mgoin <mgoin64@gmail.com>
2025-04-09 04:14:46 +00:00
4716377fbc
[Feature] Estimate max-model-len use available KV cache memory ( #16168 )
...
Signed-off-by: rongfu.leng <rongfu.leng@daocloud.io>
2025-04-08 19:12:51 -07:00
102bf967f0
[Model] Add smolvlm support ( #16017 )
...
Signed-off-by: chaunceyjiang <chaunceyjiang@gmail.com>
2025-04-08 19:12:17 -07:00
86c3369eb8
[CI/Build] Fix CI LoRA failure ( #16270 )
...
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
2025-04-09 09:13:56 +08:00
4ebc0b9640
[Bugfix] Proper input validation for multi-modal encoder-decoder models ( #16156 )
...
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
2025-04-08 09:45:21 -07:00
1f5d13ab9f
[New Model]: jinaai/jina-embeddings-v3 ( #16120 )
2025-04-08 08:39:12 -07:00
Michael Goin
Russell Bryant
Jerry Zhang
Aaron Pham
Lucas Wilkinson
Robert Shaw
bnellnm
Nick Hill
Cyrus Leung
Jee Jee Li
TJian
rongfu.leng
wang.yuqi
lkchen
Charlie Fu
vllmellm
Chen Zhang
Chauncey
hissu-hyvarinen
bwshen-mi
wwl2755
Jonathan Berkhahn
Maximilien de Bayser
Cheng Kuan Yong Jason
Isotr0py
Dipika Sikka
Frieda Huang
Ben Browning
Jinzhen Lin
Ximo Guanter
tracelogfb
Pavani Majety
Harry Mellor
Ning Xie
Shu Wang
fxmarty-amd
Jevin Jiang
Hashem Hashemi
Chanh Nguyen
Wallas Henrique
Akshat Tripathi
Bowen Bao
Yong Hoon Shin
Satyajith Chilappagari
Szymon Ożóg
Chih-Chieh Yang
Thomas Parnell
Li, Jiang
Mengqing Cao
Stan Wozniak
Nicolò Lucchesi
XiongfeiWei
Richard Zou
Caleb_Du
Andrew Sansom
Sage Moore
Huy Do
Noah Yoshida
Siyuan Liu
Alec
Marko Rosenmueller
Marco
Gabriel Marinho
Benjamin Chislett
mofanke
ponix-j
qscqesze
Michał Moskal
Alex Brooks
Lily Liu
cascade
Kaixi Hou
rasmith
Happy
Woosuk Kwon
Zijing Liu
Sangyeon Cho
Mark McLoughlin
Rui Qiao
Travis Johnson
Aleksandr Malyshev
Guillaume Calmettes
Chenyaaang
Lei Wang
Varun Sundar Rabindranath
Jeffrey Li
Chengji Yao
qizixi
Staszek Paśko
vie-serendipity
Yang Fan
Tarun Kumar
Yihua Cheng
intervitens
xsank
Shanshan Shen
Shinichi Hemmi
Angky William
Pooya Davoodi
Tyler Michael Smith
courage17340
Ryan McConville
leon-seidel
Ye (Charlotte) Qi
chaow-amd
DefTruth
Michael Goin
Nicolò Lucchesi
Yuxuan Zhang
Accelerator1996
Luka Govedič