 Roger Wangandywang96
|
7379b3d4b2
|
[V1] Fix multimodal profiling for Molmo (#11325)
Signed-off-by: ywang96 <ywang@example.com>
Co-authored-by: ywang96 <ywang@example.com>
|
2024-12-19 16:27:22 +00:00 |
|
|
Yanyi LiuandCyrus Leung
|
5aef49806d
|
[Feature] Add load generation config from model (#11164)
Signed-off-by: liuyanyi <wolfsonliu@163.com>
Signed-off-by: Yanyi Liu <wolfsonliu@163.com>
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>
|
2024-12-19 10:50:38 +00:00 |
|
|
Chen Zhang
|
c6b0a7d3ba
|
[V1] Simplify prefix caching logic by removing num_evictable_computed_blocks (#11310)
|
2024-12-19 04:17:12 +00:00 |
|
|
Alexander Matveev
|
fdea8ec167
|
[V1] VLM - enable processor cache by default (#11305)
Signed-off-by: Alexander Matveev <alexm@neuralmagic.com>
|
2024-12-18 18:54:46 -05:00 |
|
|
Cody Yu
|
bf8717ebae
|
[V1] Prefix caching for vision language models (#11187)
Signed-off-by: Cody Yu <hao.yu.cody@gmail.com>
|
2024-12-17 16:37:59 -08:00 |
|
|
Tyler Michael Smith
|
2bfdbf2a36
|
[V1][Core] Use weakref.finalize instead of atexit (#11242)
Signed-off-by: Tyler Michael Smith <tyler@neuralmagic.com>
|
2024-12-16 22:11:33 -08:00 |
|
|
Roger Wangandywang96
|
59c9b6ebeb
|
[V1][VLM] Proper memory profiling for image language models (#11210)
Signed-off-by: Roger Wang <ywang@roblox.com>
Co-authored-by: ywang96 <ywang@example.com>
|
2024-12-16 22:10:57 -08:00 |
|
|
Woosuk Kwon
|
25ebed2f8c
|
[V1][Minor] Cache np arange to reduce input preparation overhead (#11214)
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
|
2024-12-15 13:33:00 -08:00 |
|
|
Mark McLoughlin
|
6d917d0eeb
|
Enable mypy checking on V1 code (#11105)
Signed-off-by: Mark McLoughlin <markmc@redhat.com>
|
2024-12-14 09:54:04 -08:00 |
|
|
Tyler Michael Smith
|
ea7bd68d10
|
[V1][Bugfix] Fix V1 TP trust-remote-code (#11182)
Signed-off-by: Tyler Michael Smith <tyler@neuralmagic.com>
|
2024-12-14 08:21:23 +00:00 |
|
|
Cody Yu
|
9855aea21b
|
[Bugfix][V1] Re-compute an entire block when fully cache hit (#11186)
Signed-off-by: Cody Yu <hao.yu.cody@gmail.com>
|
2024-12-13 17:08:23 -08:00 |
|
|
Tyler Michael Smith
|
4b5b8a6a3b
|
[V1][Bugfix] Fix EngineCoreProc profile (#11185)
Signed-off-by: Tyler Michael Smith <tyler@neuralmagic.com>
|
2024-12-13 17:02:35 -08:00 |
|
|
Russell Bryant
|
4863e5fba5
|
[Core] V1: Use multiprocessing by default (#11074)
Signed-off-by: Russell Bryant <rbryant@redhat.com>
|
2024-12-13 16:27:32 -08:00 |
|
|
youkaichao
|
be39e3cd18
|
[core] clean up cudagraph batchsize padding logic (#10996)
Signed-off-by: youkaichao <youkaichao@gmail.com>
|
2024-12-13 06:57:50 +00:00 |
|
|
Cody Yu
|
34f1a806d5
|
[Bugfix][V1] Fix 'NoneType' object has no attribute 'hash_value' (#11157)
Signed-off-by: Cody Yu <hao.yu.cody@gmail.com>
|
2024-12-13 06:30:06 +00:00 |
|
|
Cody Yu
|
78ed8f57d8
|
[Misc][V1] Fix type in v1 prefix caching (#11151)
|
2024-12-13 00:57:40 +00:00 |
|
|
Roger Wang
|
4816d20aa4
|
[V1] Fix torch profiling for offline inference (#11125)
Signed-off-by: Roger Wang <ywang@roblox.com>
|
2024-12-12 15:51:53 +00:00 |
|
|
Woosuk Kwon
|
f092153fbe
|
[V1] Use more persistent buffers to optimize input preparation overheads (#11111)
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
|
2024-12-11 23:14:20 -08:00 |
|
|
Russell Bryant
|
ccede2b264
|
[Core] cleanup zmq ipc sockets on exit (#11115)
Signed-off-by: Russell Bryant <rbryant@redhat.com>
|
2024-12-11 19:12:24 -08:00 |
|
|
|
4e11683368
|
[V1] VLM preprocessor hashing (#11020)
Signed-off-by: Roger Wang <ywang@roblox.com>
Signed-off-by: Alexander Matveev <alexm@neuralmagic.com>
Co-authored-by: Michael Goin <michael@neuralmagic.com>
Co-authored-by: Roger Wang <ywang@roblox.com>
|
2024-12-12 00:55:30 +00:00 |
|
|
Tyler Michael Smith
|
452a723bf2
|
[V1][Core] Remove should_shutdown to simplify core process termination (#11113)
Signed-off-by: Tyler Michael Smith <tyler@neuralmagic.com>
|
2024-12-11 23:34:54 +00:00 |
|
|
Woosuk Kwon
|
d643c2aba1
|
[V1] Use input_ids as input for text-only models (#11032)
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
|
2024-12-11 10:49:23 -08:00 |
|
|
Cyrus Leung
|
cad5c0a6ed
|
[Doc] Update docs to refer to pooling models (#11093)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
|
2024-12-11 13:36:27 +00:00 |
|
|
Cyrus Leung
|
8f10d5e393
|
[Misc] Split up pooling tasks (#10820)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
|
2024-12-11 01:28:00 -08:00 |
|
|
Russell Bryant
|
61b1d2f6ae
|
[Core] v1: Use atexit to handle engine core client shutdown (#11076)
Signed-off-by: Russell Bryant <rbryant@redhat.com>
|
2024-12-11 01:26:36 -08:00 |
|
|
Mor Zusman
|
ffa48c9146
|
[Model] PP support for Mamba-like models (#10992)
Signed-off-by: mzusman <mor.zusmann@gmail.com>
|
2024-12-10 21:53:37 -05:00 |
|
|
youkaichao
|
75f89dc44c
|
[torch.compile] add a flag to track batchsize statistics (#11059)
Signed-off-by: youkaichao <youkaichao@gmail.com>
|
2024-12-10 12:40:52 -08:00 |
|
|
Joe Runde
|
9b9cef3145
|
[Bugfix] Backport request id validation to v0 (#11036)
Signed-off-by: Joe Runde <Joseph.Runde@ibm.com>
|
2024-12-10 16:38:23 +00:00 |
|
|
Tyler Michael Smith
|
28b3a1c7e5
|
[V1] Multiprocessing Tensor Parallel Support for v1 (#9856)
Signed-off-by: Tyler Michael Smith <tyler@neuralmagic.com>
|
2024-12-10 06:28:14 +00:00 |
|
|
Woosuk Kwon
|
6faec54505
|
[V1] Do not store None in self.generators (#11038)
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
|
2024-12-09 15:08:19 -08:00 |
|
|
youkaichao
|
1a2f8fb828
|
[v1] fix use compile sizes (#11000)
Signed-off-by: youkaichao <youkaichao@gmail.com>
|
2024-12-09 13:47:24 -08:00 |
|
|
Woosuk Kwon
|
3b61cb450d
|
[V1] Further reduce CPU overheads in flash-attn (#10989)
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
|
2024-12-09 12:38:46 -08:00 |
|
|
Varun Sundar RabindranathandVarun Sundar Rabindranath
|
25b79d9fd3
|
[V1] Input Batch Relocation (#10962)
Signed-off-by: Varun Sundar Rabindranath <varun@neuralmagic.com>
Co-authored-by: Varun Sundar Rabindranath <varun@neuralmagic.com>
|
2024-12-09 09:33:41 -08:00 |
|
|
Roger Wang
|
c690357928
|
[V1] Fix Detokenizer loading in AsyncLLM (#10997)
Signed-off-by: Roger Wang <ywang@roblox.com>
|
2024-12-09 16:27:10 +00:00 |
|
|
Roger Wang
|
a11f326528
|
[V1] Initial support of multimodal models for V1 re-arch (#10699)
Signed-off-by: Roger Wang <ywang@roblox.com>
|
2024-12-08 12:50:51 +00:00 |
|
|
Cyrus LeungandRoger Wang
|
955fa9533a
|
[3/N] Support and implement merged input processor for LLaVA model (#10676)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
Co-authored-by: Roger Wang <ywang@roblox.com>
|
2024-12-07 00:50:58 -08:00 |
|
|
youkaichaoandWoosuk Kwon
|
b031a455a9
|
[torch.compile] add logging for compilation time (#10941)
Signed-off-by: youkaichao <youkaichao@gmail.com>
Co-authored-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
|
2024-12-06 10:07:15 +00:00 |
|
|
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 |
|
|
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 |
|
|
|
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 |
|
|
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
|
a4c4daf364
|
[misc] use out argument for flash attention (#10822)
Signed-off-by: youkaichao <youkaichao@gmail.com>
|
2024-12-02 10:50:10 +00:00 |
|
|
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 |
|
|
Cyrus Leung
|
d2f058e76c
|
[Misc] Rename embedding classes to pooling (#10801)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
|
2024-12-01 14:36:51 +08:00 |
|
|
Woosuk Kwon
|
98f47f2a40
|
[V1] Optimize the CPU overheads in FlashAttention custom op (#10733)
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
|
2024-11-28 09:01:02 -08:00 |
|
|
Woosuk Kwon
|
a79b122400
|
[V1] Do not allocate beyond the max_model_len (#10730)
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
|
2024-11-28 00:13:15 -08:00 |
|
|
Roger Wang
|
2f0a0a17a4
|
[V1] Refactor model executable interface for multimodal models (#10570)
Signed-off-by: Roger Wang <ywang@roblox.com>
|
2024-11-26 20:46:11 +00:00 |
|
|
Kunshang Ji
|
1f6584ee85
|
[V1] Enable profile for LLMEngine (#10665)
|
2024-11-26 10:36:45 +00:00 |
|
|
Sage Mooreandyoukaichao
|
9a88f89799
|
custom allreduce + torch.compile (#10121)
Signed-off-by: youkaichao <youkaichao@gmail.com>
Co-authored-by: youkaichao <youkaichao@gmail.com>
|
2024-11-25 22:00:16 -08:00 |
|
|
Ricky Xu
|
519e8e4182
|
[v1] EngineArgs for better config handling for v1 (#10382)
Signed-off-by: rickyx <rickyx@anyscale.com>
|
2024-11-25 21:09:43 -08:00 |
|