2881 Commits

Author SHA1 Message Date
Varad Ahirwadkar
e5dc713c23
[Hardware][PowerPC] Make oneDNN dependency optional for Power (#9039)
Signed-off-by: Varad Ahirwadkar <varad.ahirwadkar1@ibm.com>
2024-10-04 17:24:42 +00:00
Simon Mo
36eecfbddb
Remove AMD Ray Summit Banner (#9075) 2024-10-04 10:17:16 -07:00
Prashant Gupta
9ade8bbc8d
[Model] add a bunch of supported lora modules for mixtral (#9008)
Signed-off-by: Prashant Gupta <prashantgupta@us.ibm.com>
2024-10-04 16:24:40 +00:00
Lucas Wilkinson
22482e495e
[Bugfix] Flash attention arches not getting set properly (#9062) 2024-10-04 09:43:15 -06:00
whyiug
3d826d2c52
[Bugfix] Reshape the dimensions of the input image embeddings in Qwen2VL (#9071) 2024-10-04 14:34:58 +00:00
Cyrus Leung
0e36fd4909
[Misc] Move registry to its own file (#9064) 2024-10-04 10:01:37 +00:00
Murali Andoorveedu
0f6d7a9a34
[Models] Add remaining model PP support (#7168)
Signed-off-by: Muralidhar Andoorveedu <muralidhar.andoorveedu@centml.ai>
Signed-off-by: Murali Andoorveedu <muralidhar.andoorveedu@centml.ai>
Co-authored-by: DarkLight1337 <tlleungac@connect.ust.hk>
2024-10-04 10:56:58 +08:00
Michael Goin
303d44790a
[Misc] Enable multi-step output streaming by default (#9047) 2024-10-03 22:55:42 -04:00
Lucas Wilkinson
aeb37c2a72
[CI/Build] Per file CUDA Archs (improve wheel size and dev build times) (#8845) 2024-10-03 22:55:25 -04:00
代君
3dbb215b38
[Frontend][Feature] support tool calling for internlm/internlm2_5-7b-chat model (#8405) 2024-10-04 10:36:39 +08:00
Domen Vreš
2838d6b38e
[Bugfix] Weight loading fix for OPT model (#9042)
Co-authored-by: dvres <dvres@fri.uni-lj.si>
2024-10-03 19:53:29 -04:00
sroy745
91add85ec4
Fix failing spec decode test (#9054) 2024-10-03 23:07:29 +00:00
youkaichao
9aaf14c62e
[misc] add forward context for attention (#9029) 2024-10-03 12:09:42 -07:00
xendo
63e39937f9
[Frontend] [Neuron] Parse literals out of override-neuron-config (#8959)
Co-authored-by: Jerzy Zagorski <jzagorsk@amazon.com>
2024-10-03 18:02:07 +00:00
sroy745
f5d72b2fc6
[Core] Make BlockSpaceManagerV2 the default BlockManager to use. (#8678) 2024-10-03 09:44:21 -07:00
Guillaume Calmettes
83caf35e08
[BugFix] Enforce Mistral ToolCall id constraint when using the Mistral tool call parser (#9020) 2024-10-03 16:44:52 +08:00
Divakar Verma
01843c89b8
[Misc] log when using default MoE config (#8971) 2024-10-03 04:31:07 +00:00
Travis Johnson
19a4dd0990
[Bugfix] example template should not add parallel_tool_prompt if tools is none (#9007) 2024-10-03 03:04:17 +00:00
Nick Hill
18c2e30c57
[Doc] Update Granite model docs (#9025) 2024-10-03 02:42:24 +00:00
Shawn Tan
19f0d25796
[Model] Adding Granite MoE. (#8206)
Co-authored-by: Nick Hill <nickhill@us.ibm.com>
2024-10-03 09:33:57 +08:00
Sergey Shlyapnikov
f58d4fccc9
[OpenVINO] Enable GPU support for OpenVINO vLLM backend (#8192) 2024-10-02 17:50:01 -04:00
Varun Sundar Rabindranath
afb050b29d
[Core] CUDA Graphs for Multi-Step + Chunked-Prefill (#8645)
Co-authored-by: Varun Sundar Rabindranath <varun@neuralmagic.com>
2024-10-02 19:44:39 +00:00
Alex Brooks
7f60520deb
[Misc] Update Default Image Mapper Error Log (#8977)
Signed-off-by: Alex-Brooks <Alex.Brooks@ibm.com>
Co-authored-by: Roger Wang <136131678+ywang96@users.noreply.github.com>
2024-10-02 11:44:38 +00:00
afeldman-nm
563649aafe
[Core] Combined support for multi-step scheduling, chunked prefill & prefix caching (#8804)
Co-authored-by: Varun Sundar Rabindranath <varun@neuralmagic.com>
Co-authored-by: Andrew Feldman <afeld2012@gmail.com>
2024-10-02 07:52:20 +00:00
Lily Liu
1570203864
[Spec Decode] (1/2) Remove batch expansion (#8839) 2024-10-01 16:04:42 -07:00
vlsav
22f5851b80
Update benchmark_serving.py to read and write json-datasets, results in UTF8, for better compatibility with Windows (#8997) 2024-10-01 11:07:06 -07:00
Cyrus Leung
4f341bd4bf
[Doc] Update list of supported models (#8987) 2024-10-02 00:35:39 +08:00
Sebastian Schoennenbeck
35bd215168
[Core] [Frontend] Priority scheduling for embeddings and in the OpenAI-API (#8965) 2024-10-01 09:58:06 +00:00
Alex Brooks
1fe0a4264a
[Bugfix] Fix Token IDs Reference for MiniCPM-V When Images are Provided With No Placeholders (#8991)
Signed-off-by: Alex-Brooks <Alex.Brooks@ibm.com>
2024-10-01 09:52:44 +00:00
Isotr0py
bc4eb65b54
[Bugfix] Fix Fuyu tensor parallel inference (#8986) 2024-10-01 17:51:41 +08:00
Divakar Verma
82f3937e59
[Misc] add process_weights_after_loading for DummyLoader (#8969) 2024-10-01 03:46:41 +00:00
youkaichao
7da2487591
[torch.compile] fix tensor alias (#8982) 2024-10-01 03:40:48 +00:00
Kevin H. Luu
aaccca2b4d
[CI/Build] Fix machete generated kernel files ordering (#8976)
Signed-off-by: kevin <kevin@anyscale.com>
Co-authored-by: Cody Yu <hao.yu.cody@gmail.com>
2024-10-01 03:33:12 +00:00
Joe Runde
062c89e7c9
[Frontend][Core] Move guided decoding params into sampling params (#8252)
Signed-off-by: Joe Runde <Joseph.Runde@ibm.com>
Co-authored-by: Nick Hill <nickhill@us.ibm.com>
2024-10-01 09:34:25 +08:00
Lily Liu
bce324487a
[CI][SpecDecode] Fix spec decode tests, use flash attention backend for spec decode CI tests. (#8975) 2024-10-01 00:51:40 +00:00
Kevin H. Luu
1425a1bcf9
[ci] Add CODEOWNERS for test directories (#8795)
Signed-off-by: kevin <kevin@anyscale.com>
2024-10-01 00:47:08 +00:00
Jee Jee Li
1cabfcefb6
[Misc] Adjust max_position_embeddings for LoRA compatibility (#8957) 2024-09-30 12:57:39 +00:00
Sebastian Schoennenbeck
be76e5aabf
[Core] Make scheduling policy settable via EngineArgs (#8956) 2024-09-30 12:28:44 +00:00
Isotr0py
2ae25f79cf
[Model] Expose InternVL2 max_dynamic_patch as a mm_processor_kwarg (#8946) 2024-09-30 13:01:20 +08:00
Jee Jee Li
8e60afa15e
[Model][LoRA]LoRA support added for MiniCPMV2.6 (#8943)
Co-authored-by: DarkLight1337 <tlleungac@connect.ust.hk>
2024-09-30 04:31:55 +00:00
Roger Wang
b6d7392579
[Misc][CI/Build] Include cv2 via mistral_common[opencv] (#8951) 2024-09-30 04:28:26 +00:00
whyiug
e01ab595d8
[Model] support input embeddings for qwen2vl (#8856) 2024-09-30 03:16:10 +00:00
Mor Zusman
f13a07b1f8
[Kernel][Model] Varlen prefill + Prefill chunking support for mamba kernels and Jamba model (#8533) 2024-09-29 17:35:58 -04:00
danieljannai21
6c9ba48fde
[Frontend] Added support for HF's new continue_final_message parameter (#8942) 2024-09-29 17:59:47 +00:00
juncheoll
1fb9c1b0bf
[Misc] Fix typo in BlockSpaceManagerV1 (#8944) 2024-09-29 15:05:54 +00:00
Nick Hill
31f46a0d35
[BugFix] Fix seeded random sampling with encoder-decoder models (#8870)
Co-authored-by: Roger Wang <ywang@roblox.com>
2024-09-29 09:43:14 +00:00
Jee Jee Li
3d49776bbb
[Model][LoRA]LoRA support added for MiniCPMV2.5 (#7199) 2024-09-29 06:59:45 +00:00
Zilin Zhu
bc2ef1f77c
[Model] Support Qwen2.5-Math-RM-72B (#8896) 2024-09-28 21:19:39 -07:00
Tyler Michael Smith
2e7fe7e79f
[Build/CI] Set FETCHCONTENT_BASE_DIR to one location for better caching (#8930) 2024-09-29 03:13:01 +00:00
Cyrus Leung
26a68d5d7e
[CI/Build] Add test decorator for minimum GPU memory (#8925) 2024-09-29 02:50:51 +00:00