3736 Commits

Author SHA1 Message Date
youkaichao
db87eb6c67
[torch.compile] use size tuning for specific sizes (#10933)
Signed-off-by: youkaichao <youkaichao@gmail.com>
2024-12-05 20:30:41 -08:00
youkaichao
9743d64e4e
[ci][build] add tests for python only compilation (#10915)
Signed-off-by: youkaichao <youkaichao@gmail.com>
2024-12-05 08:54:47 -08:00
Konrad Zawora
a43065272f
[Misc][Gaudi] Avoid torch.compile and enable lazy collectives (#10897)
Signed-off-by: Konrad Zawora <kzawora@habana.ai>
2024-12-05 08:47:46 -08:00
Isotr0py
998eeafe58
[CI/Build] Bump test transformers version (#10106)
Signed-off-by: Isotr0py <2037008807@qq.com>
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
Co-authored-by: DarkLight1337 <tlleungac@connect.ust.hk>
2024-12-05 16:05:52 +00:00
Jee Jee Li
571da8fc43
[Misc][LoRA] Clean up the function interface of Punica (#10917)
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
2024-12-05 13:22:28 +00:00
Travis Johnson
39c89e71a8
[Misc] Update llama 3.2 template to support system prompt with images (#10901)
Signed-off-by: Travis Johnson <tsjohnso@us.ibm.com>
2024-12-05 05:54:06 +00:00
Jee Jee Li
1f958a7d52
[Bugfix] Fix BNB loader target_modules (#10720)
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
2024-12-05 13:20:26 +08:00
Cyrus Leung
aa39a8e175
[Doc] Create a new "Usage" section (#10827)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
2024-12-05 11:19:35 +08:00
Michael Goin
8d370e91cb
[Bugfix] Fallback to outlines for complex json schemas (#10899)
Signed-off-by: mgoin <michael@neuralmagic.com>
2024-12-05 11:14:06 +08:00
Kevin H. Luu
7883c2bbe7
[benchmark] Make H100 benchmark optional (#10908) 2024-12-04 17:02:17 -08:00
Woosuk Kwon
2a56e1264f
[V1] Fix when max_model_len is not divisible by block_size (#10903)
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
2024-12-04 16:54:05 -08:00
Daniele
e4c34c23de
[CI/Build] improve python-only dev setup (#9621)
Signed-off-by: Daniele Trifirò <dtrifiro@redhat.com>
Signed-off-by: youkaichao <youkaichao@gmail.com>
Co-authored-by: youkaichao <youkaichao@gmail.com>
2024-12-04 21:48:13 +00:00
Chendi.Xue
82eb5ea8f3
Benchmark serving structured output (#10880)
Signed-off-by: Chendi Xue <chendi.xue@intel.com>
Co-authored-by: Michael Goin <michael@neuralmagic.com>
2024-12-04 16:28:21 -05:00
Isotr0py
10398b4706
[Model] Consolidate ViTs attention implementation without mask (#10893)
Signed-off-by: Isotr0py <2037008807@qq.com>
2024-12-04 18:11:08 +00:00
Xin Yang
01d079fd8e
[LoRA] Change lora_tokenizers capacity (#10796)
Signed-off-by: Xin Yang <xyang19@gmail.com>
2024-12-04 17:40:16 +00:00
Kevin H. Luu
c92acb9693
[ci/build] Update vLLM postmerge ECR repo (#10887) 2024-12-04 09:01:20 +00:00
jianzheng
8db957ee3a
[bugfix] fixed parameter “n” when set parameter “bestof” > 1 (#10854)
Signed-off-by: jianzheng <57654625+o2363286@users.noreply.github.com>
2024-12-04 08:48:22 +00:00
Kevin H. Luu
c9ca4fce3f
[ci/build] Job to build and push release image (#10877) 2024-12-04 15:02:40 +08:00
Kevin H. Luu
fa2dea61df
[ci/build] Change queue name for Release jobs (#10875) 2024-12-04 15:02:16 +08:00
wangxiyuan
b5b647b084
Drop ROCm load format check (#10767)
Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>
2024-12-04 04:32:21 +00:00
Tyler Michael Smith
d2bd88b122
[CI/Build] Replace mean with torch.all in test_pynccl.py (#10876)
Signed-off-by: Tyler Michael Smith <tyler@neuralmagic.com>
2024-12-04 03:23:21 +00:00
Chendi.Xue
381ac93bb5
[Benchmark] Benchmark structured output with datasets (#10557)
Signed-off-by: Aaron Pham <contact@aarnphm.xyz>
Signed-off-by: Chendi Xue <chendi.xue@intel.com>
Co-authored-by: Aaron Pham <contact@aarnphm.xyz>
2024-12-03 17:21:06 -07:00
Gregory Shtrasberg
a061fe601e
[Build][Bugfix] Using the correct type hint (#10866)
Signed-off-by: Gregory Shtrasberg <Gregory.Shtrasberg@amd.com>
2024-12-03 15:47:55 -05:00
tomeras91
7c32b6861e
[Frontend] correctly record prefill and decode time metrics (#10853)
Signed-off-by: Tomer Asida <tomera@ai21.com>
2024-12-03 19:13:31 +00:00
Michael Goin
7090c27bb2
[Bugfix] Only require XGrammar on x86 (#10865)
Signed-off-by: mgoin <michael@neuralmagic.com>
2024-12-03 10:32:21 -08:00
Yan Ma
2f2cdc745a
[MISC][XPU] quick fix for XPU CI (#10859)
Signed-off-by: yan ma <yan.ma@intel.com>
2024-12-03 17:16:31 +00:00
Alexander Matveev
3bc94cab69
[V1] VLM - Run the mm_mapper preprocessor in the frontend process (#10640)
Signed-off-by: Roger Wang <ywang@roblox.com>
Co-authored-by: Michael Goin <michael@neuralmagic.com>
Co-authored-by: Roger Wang <ywang@roblox.com>
2024-12-03 10:33:10 +00:00
Yang Zheng
f6084f6324
[Speculative Decoding] Move indices to device before filtering output (#10850)
Co-authored-by: Yang Zheng(SW)(Alex) <you@example.com>
2024-12-03 17:01:39 +08:00
Aaron Pham
9323a3153b
[Core][Performance] Add XGrammar support for guided decoding and set it as default (#10785)
Signed-off-by: Aaron Pham <contact@aarnphm.xyz>
Signed-off-by: mgoin <michael@neuralmagic.com>
Co-authored-by: mgoin <michael@neuralmagic.com>
2024-12-03 15:17:00 +08:00
Cyrus Leung
3257d449fa
[Misc] Remove deprecated names (#10817)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
2024-12-03 06:52:57 +00:00
Russell Bryant
ef51831ee8
[Doc] Add github links for source code references (#10672)
Signed-off-by: Russell Bryant <rbryant@redhat.com>
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
Co-authored-by: DarkLight1337 <tlleungac@connect.ust.hk>
2024-12-03 06:46:07 +00:00
youkaichao
dc5ce861bf
[torch.compile] remove compilation_context and simplify code (#10838)
Signed-off-by: youkaichao <youkaichao@gmail.com>
2024-12-03 06:19:02 +00:00
youkaichao
21fe7b481a
[core][distributed] add pynccl broadcast (#10843)
Signed-off-by: youkaichao <youkaichao@gmail.com>
2024-12-03 04:53:23 +00:00
Jee Jee Li
a4cf256159
[Bugfix] Fix QKVParallelLinearWithShardedLora bias bug (#10844)
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
2024-12-03 12:10:29 +08:00
zixuanzhang226
d746268e92
[Model] support bitsandbytes quantization with minicpm model (#10842)
Signed-off-by: Ubuntu <zixuanzhang@bytedance.com>
2024-12-03 03:06:41 +00:00
Michael Goin
4433195ab7
[Bugfix] Prevent benchmark_throughput.py from using duplicated random prompts (#10753) 2024-12-03 02:26:15 +00:00
Isotr0py
4c05edb33a
[Model] Add TP and BNB quantization support to LlavaMultiModalProjector (#10834)
Signed-off-by: Isotr0py <2037008807@qq.com>
Co-authored-by: Cyrus Leung <cyrus.tl.leung@gmail.com>
2024-12-02 23:06:09 +00:00
Jani Monoses
9b14d978aa
Fix openvino on GPU (#10793) 2024-12-02 18:52:19 +00:00
Yan Ma
519cc6ca12
[Misc][XPU] Avoid torch compile for XPU platform (#10747)
Signed-off-by: yan ma <yan.ma@intel.com>
Co-authored-by: youkaichao <youkaichao@gmail.com>
2024-12-02 17:53:55 +00:00
Jee Jee Li
b45f0d7946
[Misc][LoRA] Move the implementation of lora bias to punica.py (#10829)
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
2024-12-02 17:53:36 +00:00
youkaichao
a4c4daf364
[misc] use out argument for flash attention (#10822)
Signed-off-by: youkaichao <youkaichao@gmail.com>
2024-12-02 10:50:10 +00:00
Cyrus Leung
e95f275f57
[CI/Build] Update mistral_common version for tests and docs (#10825)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
2024-12-02 10:26:10 +00:00
zhou fan
ef31eabc68
[Model]: add some tests for aria model (#10770)
Signed-off-by: xffxff <1247714429@qq.com>
Signed-off-by: Isotr0py <2037008807@qq.com>
Co-authored-by: Isotr0py <2037008807@qq.com>
2024-12-02 05:36:36 +00:00
wangxiyuan
995a148575
[doc]Update config docstring (#10732)
Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>
2024-12-02 04:14:45 +00:00
youkaichao
63a164172d
[misc] remove xverse modeling file (#10814)
Signed-off-by: youkaichao <youkaichao@gmail.com>
2024-12-02 03:27:13 +00:00
Maximilien de Bayser
e25810ae29
Fill TorchSDPAAttentionMetadata seq_lens_field for prefill (#10799)
Signed-off-by: Max de Bayser <mbayser@br.ibm.com>
2024-12-02 10:05:32 +08:00
Woosuk Kwon
073a4bd1c0
[Kernel] Use out arg in flash_attn_varlen_func (#10811)
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
2024-12-01 17:55:39 -08:00
cduk
b7954776fd
[core] Avoid metrics log noise when idle - include speculative decodi… (#10809) 2024-12-02 01:49:48 +00:00
Isotr0py
b18c9bbaba
[Model] Add BNB support to Llava and Pixtral-HF (#10795)
Signed-off-by: Isotr0py <2037008807@qq.com>
2024-12-02 01:31:09 +00:00
Kuntai Du
0590ec3fd9
[Core] Implement disagg prefill by StatelessProcessGroup (#10502)
This PR provides initial support for single-node disaggregated prefill in 1P1D scenario.
Signed-off-by: KuntaiDu <kuntai@uchicago.edu>
Co-authored-by: ApostaC <yihua98@uchicago.edu>
Co-authored-by: YaoJiayi <120040070@link.cuhk.edu.cn>
2024-12-01 19:01:00 -06:00