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

2828 Commits

Author SHA1 Message Date
Akshat Tripathi
8bddb73512 [Hardware][CPU] Multi-LoRA implementation for the CPU backend (#11100) 
Signed-off-by: Akshat Tripathi <akshat@krai.ai>
Signed-off-by: Oleg Mosalov <oleg@krai.ai>
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
Co-authored-by: Oleg Mosalov <oleg@krai.ai>
Co-authored-by: Jee Jee Li <pandaleefree@gmail.com>
Co-authored-by: Isotr0py <2037008807@qq.com>
 2025-01-12 13:01:52 +00:00
Isotr0py
f967e51f38 [Model] Initialize support for Deepseek-VL2 models (#11578) 
Signed-off-by: Isotr0py <2037008807@qq.com>
Co-authored-by: Cyrus Leung <cyrus.tl.leung@gmail.com>
 2025-01-12 00:17:24 -08:00
Nicolò Lucchesi
d697dc01b4 [Bugfix] Fix RobertaModel loading (#11940) 
Signed-off-by: NickLucche <nlucches@redhat.com>
 2025-01-11 14:05:09 +00:00
Cyrus Leung
a991f7d508 [Doc] Basic guide for writing unit tests for new models (#11951) 
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
 2025-01-11 21:27:24 +08:00
Cyrus Leung
7a3a83e3b8 [CI/Build] Move model-specific multi-modal processing tests (#11934) 
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
 2025-01-11 13:50:05 +08:00
youkaichao
899136b857 [ci] fix broken distributed-tests-4-gpus (#11937) 
Signed-off-by: youkaichao <youkaichao@gmail.com>
 2025-01-11 09:07:24 +08:00
Li, Jiang
aa1e77a19c [Hardware][CPU] Support MOE models on x86 CPU (#11831) 
Signed-off-by: jiang1.li <jiang1.li@intel.com>
 2025-01-10 11:07:58 -05:00
Harry Mellor
482cdc494e [Doc] Rename offline inference examples (#11927) 
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
 2025-01-10 23:50:29 +08:00
youkaichao
241ad7b301 [ci] Fix sampler tests (#11922) 
Signed-off-by: youkaichao <youkaichao@gmail.com>
 2025-01-10 20:45:33 +08:00
Harry Mellor
d85c47d6ad Replace "online inference" with "online serving" (#11923) 
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
 2025-01-10 12:05:56 +00:00
Joe Runde
ac2f3f7fee [Bugfix] Validate lora adapters to avoid crashing server (#11727) 
Signed-off-by: Joe Runde <Joseph.Runde@ibm.com>
Co-authored-by: Jee Jee Li <pandaleefree@gmail.com>
 2025-01-10 15:56:36 +08:00
Chen Zhang
cf5f000d21 [torch.compile] Hide KV cache behind torch.compile boundary (#11677) 
Signed-off-by: Chen Zhang <zhangch99@outlook.com>
 2025-01-10 13:14:42 +08:00
Cyrus Leung
b844b99ad3 [VLM] Enable tokenized inputs for merged multi-modal processor (#11900) 
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
 2025-01-10 03:24:00 +00:00
Cyrus Leung
9a228348d2 [Misc] Provide correct Pixtral-HF chat template (#11891) 
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
 2025-01-09 10:19:37 -07:00
youkaichao
bd82872211 [ci]try to fix flaky multi-step tests (#11894) 
Signed-off-by: youkaichao <youkaichao@gmail.com>
 2025-01-09 14:47:29 +00:00
wangxiyuan
405eb8e396 [platform] Allow platform specify attention backend (#11609) 
Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>
Signed-off-by: Mengqing Cao <cmq0113@163.com>
Co-authored-by: Mengqing Cao <cmq0113@163.com>
 2025-01-09 21:46:50 +08:00
Cyrus Leung
0bd1ff4346 [Bugfix] Override dunder methods of placeholder modules (#11882) 
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
 2025-01-09 09:02:53 +00:00
Maximilien de Bayser
1fe554bac3 treat do_lower_case in the same way as the sentence-transformers library (#11815) 
Signed-off-by: Max de Bayser <mbayser@br.ibm.com>
 2025-01-09 11:05:43 +08:00
Tyler Michael Smith
615e4a5401 [CI] Turn on basic correctness tests for V1 (#10864) 2025-01-08 21:20:44 -05:00
Robert Shaw
56fe4c297c [TPU][Quantization] TPU W8A8 (#11785) 
Co-authored-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
 2025-01-08 19:33:29 +00:00
Harry Mellor
aba8d6ee00 [Doc] Move examples into categories (#11840) 
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
 2025-01-08 13:09:53 +00:00
Cyrus Leung
2a0596bc48 [VLM] Reorganize profiling/processing-related code (#11812) 
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
 2025-01-08 18:59:58 +08:00
youkaichao
889e662eae [misc] improve memory profiling (#11809) 
Signed-off-by: youkaichao <youkaichao@gmail.com>
Co-authored-by: Cyrus Leung <cyrus.tl.leung@gmail.com>
 2025-01-08 06:36:03 +00:00
Cyrus Leung
8f37be38eb [Bugfix] Comprehensively test and fix LLaVA-NeXT feature size calculation (#11800) 
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
 2025-01-07 18:25:02 +08:00
Jee Jee Li
b278557935 [Kernel][LoRA]Punica prefill kernels fusion (#11234) 
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
Signed-off-by: Abatom <abzhonghua@gmail.com>
Co-authored-by: Zhonghua Deng <abatom@163.com>
 2025-01-07 04:01:39 +00:00
Cyrus Leung
08fb75c72e [Bugfix] Fix LLaVA-NeXT feature size precision error (for real) (#11772) 
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
 2025-01-07 01:10:54 +00:00
Roger Wang
91b361ae89 [V1] Extend beyond image modality and support mixed-modality inference with Llava-OneVision (#11685) 
Signed-off-by: Roger Wang <ywang@roblox.com>
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
Co-authored-by: DarkLight1337 <tlleungac@connect.ust.hk>
 2025-01-06 19:58:16 +00:00
Chen Zhang
e20c92bb61 [Kernel] Move attn_type to Attention.__init__() (#11690) 
Signed-off-by: Chen Zhang <zhangch99@outlook.com>
 2025-01-07 00:11:28 +08:00
Jee Jee Li
32c9eff2ff [Bugfix][V1] Fix molmo text-only inputs (#11676) 
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
 2025-01-06 15:22:25 +00:00
Cyrus Leung
996357e480 [VLM] Separate out profiling-related logic (#11746) 
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
 2025-01-06 16:02:21 +08:00
Rui Qiao
022c5c6944 [V1] Refactor get_executor_cls (#11754) 2025-01-06 07:59:16 +00:00
cennn
9e764e7b10 [distributed] remove pynccl's redundant change_state (#11749) 2025-01-06 09:05:48 +08:00
cennn
635b897246 [distributed] remove pynccl's redundant stream (#11744) 2025-01-05 23:09:11 +08:00
Jee Jee Li
47831430cc [Bugfix][V1] Fix test_kv_cache_utils.py (#11738) 
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
 2025-01-04 16:07:59 +00:00
Cyrus Leung
ba214dffbe [Bugfix] Fix precision error in LLaVA-NeXT (#11735) 
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
 2025-01-04 23:45:57 +08:00
Cyrus Leung
eed11ebee9 [VLM] Merged multi-modal processors for LLaVA-NeXT-Video and LLaVA-OneVision (#11717) 
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
 2025-01-04 11:40:53 +00:00
Yan Burman
300acb8347 [Core][Bugfix] Use correct device to initialize GPU data during CUDA-graph-capture (#11233) 
Signed-off-by: Yan Burman <yanburman@users.noreply.github.com>
Signed-off-by: Ido Asraff <idoa@atero.ai>
 2025-01-04 14:50:16 +08:00
xcnick
d91457d529 [V1] Add kv cache utils tests. (#11513) 
Signed-off-by: xcnick <xcnick0412@gmail.com>
 2025-01-04 14:49:46 +08:00
Robert Shaw
80c751e7f6 [V1] Simplify Shutdown (#11659) 2025-01-03 17:25:38 +00:00
Aurick Qiao
e1a5c2f0a1 [Model] Whisper model implementation (#11280) 
Co-authored-by: Aurick Qiao <aurick.qiao@snowflake.com>
 2025-01-03 16:39:19 +08:00
Cyrus Leung
8c38ee7007 [VLM] Merged multi-modal processor for LLaVA-NeXT (#11682) 
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
 2025-01-02 16:39:27 +00:00
Cyrus Leung
a115ac46b5 [VLM] Move supported limits and max tokens to merged multi-modal processor (#11669) 
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
Signed-off-by: Isotr0py <2037008807@qq.com>
Co-authored-by: Isotr0py <2037008807@qq.com>
 2025-01-01 15:44:42 +00:00
Woosuk Kwon
73001445fb [V1] Implement Cascade Attention (#11635) 
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
 2025-01-01 21:56:46 +09:00
Jee Jee Li
11d8a091c6 [Misc] Optimize Qwen2-VL LoRA test (#11663) 
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
 2025-01-01 14:42:23 +08:00
Cyrus Leung
365801fedd [VLM] Add max-count checking in data parser for single image models (#11661) 
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
Signed-off-by: Roger Wang <ywang@roblox.com>
Co-authored-by: Roger Wang <ywang@roblox.com>
 2024-12-31 22:15:21 -08:00
Joe Runde
4db72e57f6 [Bugfix][Refactor] Unify model management in frontend (#11660) 
Signed-off-by: Joe Runde <Joseph.Runde@ibm.com>
 2025-01-01 02:21:51 +00:00
Roger Wang
e7c7c5e822 [V1][VLM] V1 support for selected single-image models. (#11632) 
Signed-off-by: Roger Wang <ywang@roblox.com>
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
Signed-off-by: Isotr0py <2037008807@qq.com>
Co-authored-by: DarkLight1337 <tlleungac@connect.ust.hk>
Co-authored-by: Isotr0py <2037008807@qq.com>
 2024-12-31 21:17:22 +00:00
Chen Zhang
8c3230d8c1 [V1] Simpify vision block hash for prefix caching by removing offset from hash (#11646) 2024-12-31 08:56:01 +00:00
sakunkun
2c5718809b [Bugfix] Move the _touch(computed_blocks) call in the allocate_slots method to after the check for allocating new blocks. (#11565) 2024-12-31 06:29:04 +00:00
John Giorgi
82c49d3260 [Misc][LoRA] Support Rank Stabilized LoRA (RSLoRA) (#6909) 
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
Co-authored-by: Jee Jee Li <pandaleefree@gmail.com>
 2024-12-30 22:15:58 -08:00