6026 Commits

Author SHA1 Message Date
youkaichao
c301616ed2
[ci][tests] add gh200 tests (#11244)
Signed-off-by: youkaichao <youkaichao@gmail.com>
2024-12-16 15:53:18 -08:00
bk-TurbaAI
35ffa682b1
[Docs] hint to enable use of GPU performance counters in profiling tools for multi-node distributed serving (#11235)
Co-authored-by: Michael Goin <michael@neuralmagic.com>
2024-12-16 22:20:39 +00:00
youkaichao
551603feff
[core] overhaul memory profiling and fix backward compatibility (#10511)
Signed-off-by: youkaichao <youkaichao@gmail.com>
2024-12-16 13:32:25 -08:00
Varun Sundar Rabindranath
efbce85f4d
[misc] Layerwise profile updates (#10242)
Signed-off-by: Varun Sundar Rabindranath <varun@neuralmagic.com>
Co-authored-by: Varun Sundar Rabindranath <varun@neuralmagic.com>
2024-12-16 18:14:57 +00:00
Isotr0py
2ca830dbaa
[Doc] Reorder vision language examples in alphabet order (#11228)
Signed-off-by: Isotr0py <2037008807@qq.com>
2024-12-16 11:23:33 +00:00
Isotr0py
d927dbcd88
[Model] Refactor Ultravox to use merged input processor (#11198)
Signed-off-by: Isotr0py <2037008807@qq.com>
Co-authored-by: Cyrus Leung <cyrus.tl.leung@gmail.com>
2024-12-16 10:09:53 +00:00
Jani Monoses
bddbbcb132
[Model] Support Cohere2ForCausalLM (Cohere R7B) (#11203) 2024-12-16 09:56:19 +00:00
cennn
b3b1526f03
WIP: [CI/Build] simplify Dockerfile build for ARM64 / GH200 (#11212)
Signed-off-by: drikster80 <ed.sealing@gmail.com>
Co-authored-by: drikster80 <ed.sealing@gmail.com>
2024-12-16 09:20:49 +00:00
yansh97
17138af7c4
[Bugfix] Fix the default value for temperature in ChatCompletionRequest (#11219) 2024-12-16 00:15:40 -08:00
chenqianfzh
69ba344de8
[Bugfix] Fix block size validation (#10938) 2024-12-15 16:38:40 -08:00
AlexHe99
da6f409246
Update deploying_with_k8s.rst (#10922) 2024-12-15 16:33:58 -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
shangmingc
d263bd9df7
[Core] Support disaggregated prefill with Mooncake Transfer Engine (#10884)
Signed-off-by: Shangming Cai <caishangming@linux.alibaba.com>
2024-12-15 21:28:18 +00:00
Kuntai Du
38e599d6a8
[Doc] add documentation for disaggregated prefilling (#11197)
Signed-off-by: Kuntai Du <kuntai@uchicago.edu>
2024-12-15 13:31:16 -06:00
Cyrus Leung
96d673e0f8
[Bugfix] Fix error handling of unsupported sliding window (#11213)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
2024-12-15 10:59:42 -07:00
Cyrus Leung
b10609e6a1
[Misc] Clean up multi-modal processor (#11207)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
2024-12-15 06:30:28 +00:00
youkaichao
a1c02058ba
[torch.compile] allow tracking forward time (#11081)
Signed-off-by: youkaichao <youkaichao@gmail.com>
2024-12-14 19:45:00 -08:00
Jee Jee Li
15859f2357
[[Misc]Upgrade bitsandbytes to the latest version 0.45.0 (#11201) 2024-12-15 03:03:06 +00:00
Sungjae Lee
886936837c
[Performance][Core] Optimize the performance of evictor v1 and v2 by applying a priority queue and lazy deletion (#7209) 2024-12-14 11:38:10 -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
Cyrus Leung
93abf23a64
[VLM] Fully dynamic prompt replacement in merged input processor (#11199)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
2024-12-14 17:52:18 +00:00
Brad Hilton
9c3dadd1c9
[Frontend] Add logits_processors as an extra completion argument (#11150)
Signed-off-by: Brad Hilton <brad.hilton.nw@gmail.com>
2024-12-14 16:46:42 +00:00
Jee Jee Li
3cb5769883
[Misc] Minor improvements to the readability of PunicaWrapperBase (#11200)
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
2024-12-14 16:38:27 +00:00
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
Russell Bryant
48259264a4
[Core] Update outlines and increase its threadpool size (#11140)
Signed-off-by: Russell Bryant <rbryant@redhat.com>
2024-12-14 07:46:18 +00:00
dhuangnm
24a3d12b82
update compressed-tensors to latest version (#11183)
Co-authored-by: dhuangnm <dhuang@MacBook-Pro-2.local>
2024-12-14 03:22:44 +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
Jiaxin Shan
0d8451c3a4
[Distributed] Allow the placement group more time to wait for resources to be ready (#11138)
Signed-off-by: Jiaxin Shan <seedjeffwan@gmail.com>
2024-12-13 20:17:37 +00:00
Jani Monoses
0a56bcc03d
[Bugfix][Hardware][CPU] Enable Gemma2 with SDPA on CPU backend (#11169) 2024-12-13 18:00:40 +00:00
Cyrus Leung
0920ab9131
[Doc] Reorganize online pooling APIs (#11172)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
2024-12-14 00:22:22 +08:00
Alexander Matveev
238c0d93b4
[Misc] Add tokenizer_mode param to benchmark_serving.py (#11174)
Signed-off-by: Alexander Matveev <alexm@neuralmagic.com>
2024-12-13 16:19:10 +00:00
zhangjf
5b0ed8391d
[Bugfix] using len(tokenizer) instead of tokenizer.vocab_size in AllowedTokenIdsLogitsProcessor (#11156) 2024-12-13 15:56:19 +00:00
Sungjae Lee
c31d4a57a6
[Core] support LoRA and prompt adapter in content-based hashing for Block Manager v2 prefix caching (#8240) 2024-12-13 07:51:25 -08:00
Chenguang Li
d1fa714cb1
[Refactor]A simple device-related refactor (#11163)
Signed-off-by: noemotiovon <noemotiovon@gmail.com>
Co-authored-by: noemotiovon <noemotiovon@gmail.com>
2024-12-13 13:39:00 +00:00
Roger Wang
969da7d70b
[V1][VLM] Fix edge case bug for InternVL2 (#11165)
Signed-off-by: Roger Wang <ywang@roblox.com>
2024-12-13 11:09:30 +00:00
Cyrus Leung
eeec9e3390
[Frontend] Separate pooling APIs in offline inference (#11129)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
2024-12-13 10:40:07 +00:00
Li, Jiang
f93bf2b189
[Bugfix][CI][CPU] add missing datasets package to requirements-cpu.txt (#11159)
Signed-off-by: jiang1.li <jiang1.li@intel.com>
2024-12-13 08:50:35 +00:00
Jani Monoses
7cd7409142
PaliGemma 2 support (#11142) 2024-12-13 07:40:07 +00:00
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
Gregory Shtrasberg
00c1bde5d8
[ROCm][AMD] Disable auto enabling chunked prefill on ROCm (#11146)
Signed-off-by: Gregory Shtrasberg <Gregory.Shtrasberg@amd.com>
2024-12-13 05:31:26 +00:00
Dipika Sikka
3989a79824
[Bugfix] Update starcoder2 to remap k/v scale names for kv_cache quantization (#11148) 2024-12-13 05:07:20 +00:00
Pooya Davoodi
1efce68605
[Bugfix] Use runner_type instead of task in GritLM (#11144)
Signed-off-by: Pooya Davoodi <pooya.davoodi@parasail.io>
2024-12-13 04:09:53 +00:00
Luka Govedič
30870b4f66
[torch.compile] Dynamic fp8 + rms_norm fusion (#10906)
Signed-off-by: luka <luka@neuralmagic.com>
Co-authored-by: Varun Sundar Rabindranath <varun@neuralmagic.com>
2024-12-13 03:19:23 +00:00
Cody Yu
78ed8f57d8
[Misc][V1] Fix type in v1 prefix caching (#11151) 2024-12-13 00:57:40 +00:00
shangmingc
db6c264a1e
[Bugfix] Fix value unpack error of simple connector for KVCache transfer. (#11058)
Signed-off-by: ShangmingCai <csmthu@gmail.com>
2024-12-12 21:19:17 +00:00
Jeremy Arnold
9f3974a319
Fix logging of the vLLM Config (#11143) 2024-12-12 12:05:57 -08:00
Cody Yu
2c97eca1ff
[Misc] Validate grammar and fail early (#11119) 2024-12-12 18:34:26 +00:00