biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity
9,263 Commits 2 Branches 140 Tags
b9a1c4c8a2430555f1959938b87b10640c751e57
Commit Graph

9263 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
Cyrus Leung
951b038298 [Misc] Move jsontree to utils (#22622) 
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
 2025-08-11 03:49:32 -07:00
Cyrus Leung
ebf7605b0d [Misc] Move tensor schema tests (#22612) 
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
 2025-08-11 00:15:27 -07:00
Harry Mellor
bc1d02ac85 [Docs] Add comprehensive CLI reference for all large vllm subcommands (#22601) 
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
 2025-08-11 00:13:33 -07:00
JartX
1e55dfa7e5 [BUGFIX] KeyError 'layers.14.mlp.gate.g_idx' for Qwen3-MoE with GPTQ on ROCm (#22017) 2025-08-11 00:13:30 -07:00
Jee Jee Li
384a052971 [Misc] benchmark_moe supports expert parallel (#22251) 
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
 2025-08-11 00:13:27 -07:00
Maximilien de Bayser
39052dbca8 Support token_type_ids in V1 with less code changes (#21985) 
Signed-off-by: Max de Bayser <mbayser@br.ibm.com>
 2025-08-10 22:54:59 -07:00
vllmellm
9c97a1c349 [ROCm][AITER] Support AITER Rope ops in RotaryEmbedding Module. (#22521) 
Signed-off-by: vllmellm <vllm.ellm@embeddedllm.com>
 2025-08-10 22:52:34 -07:00
Eugene Cheah
f919d4cb8f [BugFix] Fix logits repetition penalty cuda check (#22592) 2025-08-10 22:52:31 -07:00
Zhewen Li
afa5b7ca0b [Misc][gpt-oss] guard import when triton kernel when not up to date (#22584) 
Signed-off-by: zhewenli <zhewenli@meta.com>
 2025-08-10 21:29:35 -07:00
Lifans
1b99028069 [Misc][gpt-oss] Add rules to label gpt-oss related PRs (#22600) 
Signed-off-by: Lifan Shen <lifans@meta.com>
 2025-08-10 19:49:51 -07:00
Nick Hill
5898b135ab [BugFix] Fix KVConnectorOutput TPU breakage (#22598) 
Signed-off-by: Nick Hill <nhill@redhat.com>
 2025-08-10 19:33:48 -07:00
22quinn
b799f4b9ea [CI/Build] Fix tensorizer test for load_format change (#22583) 
Signed-off-by: 22quinn <33176974+22quinn@users.noreply.github.com>
 2025-08-10 19:30:00 -07:00
Benji Beck
06da44f0cb Migrate LlavaImageInputs to TensorSchema (#21770) 
Signed-off-by: Benji Beck <benjibeck@meta.com>
 2025-08-10 19:29:19 -07:00
Benji Beck
a554991748 Migrate LlavaNextVideoPixelInputs to TensorSchema (#21843) 
Signed-off-by: Benji Beck <benjibeck@meta.com>
 2025-08-10 19:29:16 -07:00
Doug Smith
d1af8b7be9 enable Docker-aware precompiled wheel setup (#22106) 
Signed-off-by: dougbtv <dosmith@redhat.com>
 2025-08-10 16:29:02 -07:00
Benji Beck
68b254d673 Fix TensorSchema validation test for symbolic dims (#22366) 
Signed-off-by: Benji Beck <benjibeck@meta.com>
 2025-08-10 17:16:44 +00:00
ZiTian Zhao
8c50d62f5a Remove redundant row_indices unsqueeze operation in MiniCPMO (#22528) 
Signed-off-by: zitian.zhao <zitian.zhao@tencentmusic.com>
 2025-08-10 09:20:00 -07:00
Benji Beck
b4e2916721 Migrate LlavaNextImageInputs to TensorSchema (#21774) 
Signed-off-by: Benji Beck <benjibeck@meta.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
 2025-08-10 09:05:21 -07:00
Breno Baldas Skuk
65a7917be4 Fix(benchmarks): allow multiple mm contents in OpenAI Chat Completion Benchmarks (#22534) 
Signed-off-by: breno.skuk <breno.skuk@hcompany.ai>
 2025-08-10 09:03:15 -07:00
Isotr0py
b76753f0b5 [Bugfix][Kernel] Support partial rotary embedding for MRoPE triton kernel (#22593) 
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
 2025-08-10 09:00:36 -07:00
youkaichao
b81fe83b2c [doc] add alibaba cloud as sponsor (#22597) 
Signed-off-by: youkaichao <youkaichao@gmail.com>
 2025-08-10 23:13:47 +08:00
youkaichao
0757551c96 [doc] add beijing meetup links (#22596) 
Signed-off-by: youkaichao <youkaichao@gmail.com>
 2025-08-10 22:51:36 +08:00
Harry Mellor
8290d15d2c Move CacheConfig from config/__init__.py to config/cache.py (#22586) 
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
 2025-08-10 07:36:40 -07:00
Isotr0py
049c245143 [Misc] Replace flaky image urls in pixtral test (#22574) 
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
Signed-off-by: Isotr0py <2037008807@qq.com>
 2025-08-10 06:18:21 -07:00
Harry Mellor
00976db0c3 [Docs] Fix warnings in docs build (#22588) 
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
 2025-08-10 05:49:51 -07:00
Cyrus Leung
d411df0296 [Misc] Further refine type annotations in parallel state (#22499) 
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
 2025-08-10 05:49:48 -07:00
22quinn
010e0e39ea [Doc] Fix API doc link in side navigation (#22585) 
Signed-off-by: 22quinn <33176974+22quinn@users.noreply.github.com>
 2025-08-10 01:35:22 -07:00
Ning Xie
326976291b [Misc] code clean duplicate set_current_vllm_config in _set_vllm_config (#22566) 
Signed-off-by: Andy Xie <andy.xning@gmail.com>
 2025-08-10 00:08:48 -07:00
Isotr0py
7e8d685775 [Minor] Fix pre-commit error on main (#22579) 
Signed-off-by: Isotr0py <2037008807@qq.com>
 2025-08-10 00:08:23 -07:00
Harry Mellor
c49848396d Refactor sliding window configuration to Transformers best practice (#21927) 
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
 2025-08-09 20:50:48 -07:00
Chengji Yao
2a84fb422f [TPU] kv cache update kernel doesn't need to be padded slices to multiple of num_slices_per_block (#22394) 
Signed-off-by: Chengji Yao <chengjiyao@gmail.com>
Co-authored-by: Chengji Yao <chengjiyao@gmail.com>
 2025-08-09 20:49:04 -07:00
ZiTian Zhao
534c45b962 Improve fast_topk function with type hints and documentation (#22530) 
Signed-off-by: zitian.zhao <zitian.zhao@tencentmusic.com>
 2025-08-09 20:25:42 -07:00
Le Chen
3d7363e61c [Config] add "qwen" as a native eagle3 target supported model (#22333) 
Signed-off-by: lechen <lecself@163.com>
Signed-off-by: LeChen <lecself@163.com>
 2025-08-09 20:21:05 -07:00
Jee Jee Li
0c5254b82a [oss] Init gpt-oss bf16 support (#22508) 
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
 2025-08-09 20:19:13 -07:00
Thomas Parnell
61f67d8acd [V1] [Hybrid] Enable Full CUDA Graph (decode-only) for Mamba layers (#21401) 
Signed-off-by: Thomas Parnell <tpa@zurich.ibm.com>
 2025-08-09 20:16:11 -07:00
TJian
42172ad18f [FEAT] [Performance] Add triton mrope to replace the torch code path (#22375) 
Signed-off-by: tjtanaa <tunjian.tan@embeddedllm.com>
 2025-08-09 11:50:03 -07:00
Isotr0py
fbd8595c5c [Bugfix] Fix basic models tests hanging due to mm processor creation (#22571) 
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
 2025-08-09 11:42:21 -07:00
Nicolò Lucchesi
5a16fa614c [Model] Gemma3n MM (#20495) 
Signed-off-by: ShriKode <shrikode@gmail.com>
Signed-off-by: NickLucche <nlucches@redhat.com>
Signed-off-by: Roger Wang <hey@rogerw.me>
Co-authored-by: ShriKode <shrikode@gmail.com>
Co-authored-by: Roger Wang <hey@rogerw.me>
 2025-08-09 09:56:25 -07:00
Harry Mellor
2d18256e47 Move ParallelConfig from config/__init__.py to config/parallel.py (#22565) 
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
 2025-08-09 08:33:46 -07:00
Harry Mellor
56186474f6 [Docs] Reduce noise in docs and --help from the JSON tip (#22567) 
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
 2025-08-09 08:31:32 -07:00
Thomas Parnell
1bf5e1f25b [CI] [Hybrid] Speed up hybrid models test by removing large models (#22563) 
Signed-off-by: Thomas Parnell <tpa@zurich.ibm.com>
 2025-08-09 02:04:42 -07:00
Yuxuan Zhang
a6022e6fbc GLM-4.5V with new class name at transformers (#22520) 
Signed-off-by: zRzRzRzRzRzRzR <2448370773@qq.com>
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
Co-authored-by: Isotr0py <mozf@mail2.sysu.edu.cn>
 2025-08-09 00:50:21 -07:00
Thomas Parnell
2be07a0db1 Update docs for Minimax-Text support (#22562) 
Signed-off-by: Thomas Parnell <tpa@zurich.ibm.com>
 2025-08-09 00:18:18 -07:00
Jee Jee Li
0edc0cd52b [Bugfix] Fix CI moe kernel failure (#22556) 
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
 2025-08-09 00:03:29 -07:00
Isotr0py
7920e9b1c5 [Bugfix] Fix failing GPT-OSS initialization test (#22557) 
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
 2025-08-09 00:03:26 -07:00
Charlie Fu
b7c0942b65 [ROCm][Misc] Rename the context_len to seq_len in ROCm custom paged attention kernel (#22097) 
Signed-off-by: charlifu <charlifu@amd.com>
 2025-08-08 23:15:06 -07:00
Kyuyeun Kim
9a0c5ded5a [TPU] Add support for online w8a8 quantization (#22425) 
Signed-off-by: Kyuyeun Kim <kyuyeunk@google.com>
 2025-08-08 23:12:54 -07:00
Eldar Kurtić
10a02535d4 Fix loading of quantized BigCode models (#22463) 
Signed-off-by: Eldar Kurtic <eldar@neuralmagic.com>
 2025-08-08 23:12:12 -07:00
Cyrus Leung
65552b476b [Misc] Use config definitions from Transformers library (#21913) 
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
 2025-08-08 23:10:51 -07:00
Or Ozeri
7ad7adb67f v1: Pass KVConnectorOutput to scheduler-side (#22157) 
Signed-off-by: Or Ozeri <oro@il.ibm.com>
 2025-08-08 23:09:51 -07:00