5db6b2c961
[V1][BugFix] Fix remaining sync engine client shutdown errors/hangs ( #13869 )
...
Signed-off-by: Nick Hill <nhill@redhat.com >
2025-03-04 15:06:47 +00:00
c060b71408
[Model] Add support for GraniteMoeShared models ( #13313 )
...
Signed-off-by: Travis Johnson <tsjohnso@us.ibm.com >
Co-authored-by: Cyrus Leung <cyrus.tl.leung@gmail.com >
2025-03-04 08:04:52 +08:00
ae122b1cbd
[WIP][[V1][Metrics] Implement max_num_generation_tokens, request_params_n, and request_params_max_tokens metrics ( #14055 )
...
Signed-off-by: Mark McLoughlin <markmc@redhat.com >
2025-03-03 19:04:45 +00:00
848a6438ae
[ROCm] Faster Custom Paged Attention kernels ( #12348 )
2025-03-03 09:24:45 -08:00
f35f8e2242
[Build] Make sure local main branch is synced when VLLM_USE_PRECOMPILED=1 ( #13921 )
...
Signed-off-by: Cody Yu <hao.yu.cody@gmail.com >
2025-03-03 16:43:14 +08:00
cf069aa8aa
Update deprecated Python 3.8 typing ( #13971 )
2025-03-02 17:34:51 -08:00
bf33700ecd
[v0][structured output] Support reasoning output ( #12955 )
...
Signed-off-by: Ce Gao <cegao@tensorchord.ai >
2025-03-02 14:49:42 -05:00
cc5e8f6db8
[Model] Add LoRA support for TransformersModel ( #13770 )
...
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com >
2025-03-02 09:17:34 +08:00
6a92ff93e1
[Misc][Kernel]: Add GPTQAllSpark Quantization ( #12931 )
2025-02-28 22:30:59 -08:00
bd56c983d6
[torch.compile] Fix RMSNorm + quant fusion in the non-cutlass-fp8 case, rename RedundantReshapesPass to NoopEliminationPass ( #10902 )
...
Signed-off-by: luka <luka@neuralmagic.com >
2025-02-28 16:20:11 -07:00
28943d36ce
[v1] Move block pool operations to a separate class ( #13973 )
...
Signed-off-by: Chen Zhang <zhangch99@outlook.com >
Co-authored-by: Cody Yu <hao.yu.cody@gmail.com >
2025-02-28 20:53:31 +00:00
e7bd944e08
[v1] Cleanup the BlockTable in InputBatch ( #13977 )
...
Signed-off-by: Chen Zhang <zhangch99@outlook.com >
2025-02-28 19:03:16 +00:00
4be4b26cb7
Fix entrypoint tests for embedding models ( #14052 )
2025-02-28 08:56:44 -08:00
f7bee5c815
[VLM][Bugfix] Enable specifying prompt target via index ( #14038 )
2025-02-28 07:35:55 -08:00
76c89fcadd
Use smaller embedding model when not testing model specifically ( #13891 )
2025-02-28 00:50:43 -08:00
73e0225ee9
[Bugfix] Check that number of images matches number of <|image|> tokens with mllama ( #13911 )
...
Signed-off-by: Travis Johnson <tsjohnso@us.ibm.com >
2025-02-28 04:00:45 +00:00
38acae6e97
[ROCm] Fix the Kernels, Core, and Prefix Caching AMD CI groups ( #13970 )
...
Signed-off-by: Sage Moore <sage@neuralmagic.com >
2025-02-27 20:31:47 +00:00
f1579b229d
[VLM] Generalized prompt updates for multi-modal processor ( #13964 )
...
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk >
2025-02-27 17:44:25 +00:00
edf309ebbe
[VLM] Support multimodal inputs for Florence-2 models ( #13320 )
2025-02-27 02:06:41 -08:00
788f284b53
Fix test_block_fp8.py test for MoE ( #13915 )
...
Signed-off-by: mgoin <mgoin64@gmail.com >
2025-02-27 18:00:00 +08:00
cd711c48b2
[V1][Metrics] Handle preemptions ( #13169 )
2025-02-26 20:04:59 -08:00
c9944acbf9
[misc] Rename Ray ADAG to Compiled Graph ( #13928 )
2025-02-26 20:03:28 -08:00
f95903909f
[Kernel] FlashMLA integration ( #13747 )
...
Signed-off-by: Lucas Wilkinson <lwilkinson@neuralmagic.com >
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com >
2025-02-27 10:35:08 +08:00
4cb6fa0a9c
[Bugfix] Backend option to disable xgrammar any_whitespace ( #12744 )
...
Signed-off-by: Wallas Santos <wallashss@ibm.com >
Signed-off-by: Joe Runde <Joseph.Runde@ibm.com >
Co-authored-by: Joe Runde <Joseph.Runde@ibm.com >
2025-02-26 10:52:34 -08:00
934bb99c71
[Bugfix] Update expected token counts for Ultravox tests ( #13895 )
2025-02-26 04:56:50 -08:00
3f808cc044
[Bugfix] Do not crash V0 engine on input errors ( #13101 )
...
Signed-off-by: Joe Runde <Joseph.Runde@ibm.com >
2025-02-26 19:07:29 +08:00
215bf150a6
[Bugfix] Handle None parameters in Mistral function calls. ( #13786 )
2025-02-26 03:06:21 -08:00
7b700ec8c8
[Bugfix] Add test example for Ultravox v0.5 ( #13890 )
2025-02-26 02:31:43 -08:00
7ca1da020f
[Misc] Fix input processing for Ultravox ( #13871 )
2025-02-25 23:56:34 -08:00
5157338ed9
[Misc] Improve LoRA spelling ( #13831 )
2025-02-25 23:43:01 -08:00
145944cb94
Improve pipeline partitioning ( #13839 )
2025-02-25 18:53:56 -08:00
5629f26df7
[V1][Spec Decode] Change Spec Decode Rejection Sampling API ( #13729 )
2025-02-25 18:14:48 -08:00
07c4353057
[Model] Support Grok1 ( #13795 )
...
Signed-off-by: mgoin <mgoin64@gmail.com >
2025-02-26 01:07:12 +00:00
34e3494e70
Fix failing MyGemma2Embedding test ( #13820 )
...
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com >
2025-02-25 12:33:03 -08:00
f75aa72732
[Neuron] Add custom_ops for neuron backend ( #13246 )
...
Signed-off-by: Liangfu Chen <liangfc@amazon.com >
Co-authored-by: George Novack <gnovack@amazon.com >
Co-authored-by: Aoyu Zhang <aoyuzhan@amazon.com >
2025-02-25 11:47:49 -08:00
37b6cb4985
[CI/Build] Fix V1 LoRA failure ( #13767 )
2025-02-25 02:01:15 -08:00
aabeb2688f
[ROCm][Quantization][Kernel] Using HIP FP8 header ( #12593 )
2025-02-25 00:39:59 -08:00
03f48b3db6
[Core] LoRA V1 - Add add/pin/list/remove_lora functions ( #13705 )
2025-02-25 00:18:02 -08:00
cdc1fa12eb
Remove unused kwargs from model definitions ( #13555 )
2025-02-24 17:13:52 -08:00
befc402d34
[V1] V1 engine implements parallel sampling (AsyncLLM and LLMEngine) ( #10980 )
...
Signed-off-by: Andrew Feldman <afeldman@neuralmagic.com >
Co-authored-by: Nick Hill <nhill@redhat.com >
2025-02-24 08:29:41 -08:00
781096e385
Expert Parallelism (EP) Support for DeepSeek V2 ( #12583 )
2025-02-24 07:33:20 -08:00
f90a375593
[ci] Add logic to change model to S3 path only when S3 CI env var is on ( #13727 )
...
Signed-off-by: <>
Co-authored-by: EC2 Default User <ec2-user@ip-172-31-63-253.us-west-2.compute.internal >
2025-02-24 06:32:11 +00:00
cbae7af552
[V1][BugFix] Fix engine core client shutdown hangs ( #13298 )
...
Even though ZMQ context.destroy() is meant to close open sockets before terminating the context, it appears to be necessary to do this explicitly or else it can hang in the context.term() method.
Close zmq sockets explicitly before terminating context, make shutdown of client resource more robust, shut down engine core process prior to terminating zmq context.
Signed-off-by: Nick Hill <nhill@redhat.com >
2025-02-23 13:07:43 -08:00
eb24dc4a45
[v1] torchrun compatibility ( #13642 )
...
Signed-off-by: youkaichao <youkaichao@gmail.com >
2025-02-23 22:47:24 +08:00
ba5106e519
[LMM] Implement merged multimodal processor for whisper ( #13278 )
2025-02-23 01:46:03 -08:00
2c5e637b57
[ci] Use env var to control whether to use S3 bucket in CI ( #13634 )
2025-02-22 19:19:45 -08:00
558db8083c
[V1][Kernel] Refactor the prefix_prefill kernel so that the caller no longer has to pass in the context lengths ( #13095 )
2025-02-22 05:25:41 -08:00
e109e598c7
[NVIDIA] Support nvfp4 cutlass gemm ( #13571 )
2025-02-22 05:24:05 -08:00
8db1b9d0a1
Support SSL Key Rotation in HTTP Server ( #13495 )
2025-02-22 05:17:44 -08:00
105b8ce4c0
[Misc] Reduce LoRA-related static variable ( #13166 )
2025-02-22 00:21:30 -08:00
Nick Hill