4180 Commits

Author SHA1 Message Date
Isotr0py
d75ab55f10
[Misc] Add deepseek_vl2 chat template (#12143)
Signed-off-by: Isotr0py <2037008807@qq.com>
2025-01-17 06:34:48 +00:00
Chen Zhang
d1adb9b403
[BugFix] add more is not None check in VllmConfig.__post_init__ (#12138)
Signed-off-by: Chen Zhang <zhangch99@outlook.com>
2025-01-17 05:33:22 +00:00
Yuan Tang
b8bfa46a18
[Bugfix] Fix issues in CPU build Dockerfile (#12135)
Signed-off-by: Yuan Tang <terrytangyuan@gmail.com>
2025-01-17 12:54:01 +08:00
Yuan Tang
1475847a14
[Doc] Add instructions on using Podman when SELinux is active (#12136)
Signed-off-by: Yuan Tang <terrytangyuan@gmail.com>
2025-01-17 04:45:36 +00:00
Kunshang Ji
fead53ba78
[CI]add genai-perf benchmark in nightly benchmark (#10704)
Signed-off-by: Kunshang Ji <kunshang.ji@intel.com>
2025-01-17 04:15:09 +00:00
Kuntai Du
ebc73f2828
[Bugfix] Fix a path bug in disaggregated prefill example script. (#12121)
Signed-off-by: Kuntai Du <kuntai@uchicago.edu>
2025-01-17 11:12:41 +08:00
Chen Zhang
d06e824006
[Bugfix] Set enforce_eager automatically for mllama (#12127)
Signed-off-by: Chen Zhang <zhangch99@outlook.com>
2025-01-16 15:30:08 -05:00
Isotr0py
62b06ba23d
[Model] Add support for deepseek-vl2-tiny model (#12068)
Signed-off-by: Isotr0py <2037008807@qq.com>
2025-01-16 17:14:48 +00:00
Varun Sundar Rabindranath
5fd24ec02e
[misc] Add LoRA kernel micro benchmarks (#11579) 2025-01-16 15:51:40 +00:00
Roger Wang
874f7c292a
[Bugfix] Fix max image feature size for Llava-one-vision (#12104)
Signed-off-by: Roger Wang <ywang@roblox.com>
2025-01-16 14:54:06 +00:00
youkaichao
92e793d91a
[core] LLM.collective_rpc interface and RLHF example (#12084)
Signed-off-by: youkaichao <youkaichao@gmail.com>
2025-01-16 20:19:52 +08:00
youkaichao
bf53e0c70b
Support torchrun and SPMD-style offline inference (#12071)
Signed-off-by: youkaichao <youkaichao@gmail.com>
2025-01-16 19:58:53 +08:00
Isotr0py
dd7c9ad870
[Bugfix] Remove hardcoded head_size=256 for Deepseek v2 and v3 (#12067)
Signed-off-by: Isotr0py <2037008807@qq.com>
2025-01-16 10:11:54 +00:00
Michael Goin
9aa1519f08
Various cosmetic/comment fixes (#12089)
Signed-off-by: mgoin <michael@neuralmagic.com>
2025-01-16 09:59:06 +00:00
Cyrus Leung
f8ef146f03
[Doc] Add documentation for specifying model architecture (#12105) 2025-01-16 15:53:43 +08:00
Elfie Guo
fa0050db08
[Core] Default to using per_token quantization for fp8 when cutlass is supported. (#8651)
Signed-off-by: mgoin <michael@neuralmagic.com>
Co-authored-by: Michael Goin <mgoin@redhat.com>
Co-authored-by: mgoin <michael@neuralmagic.com>
2025-01-16 04:31:27 +00:00
tvirolai-amd
cd9d06fb8d
Allow hip sources to be directly included when compiling for rocm. (#12087) 2025-01-15 16:46:03 -05:00
Varun Sundar Rabindranath
ebd8c669ef
[Bugfix] Fix _get_lora_device for HQQ marlin (#12090)
Signed-off-by: Varun Sundar Rabindranath <varun@neuralmagic.com>
Co-authored-by: Varun Sundar Rabindranath <varun@neuralmagic.com>
2025-01-15 19:59:42 +00:00
Roger Wang
70755e819e
[V1][Core] Autotune encoder cache budget (#11895)
Signed-off-by: Roger Wang <ywang@roblox.com>
2025-01-15 11:29:00 -08:00
Joe Runde
edce722eaa
[Bugfix] use right truncation for non-generative tasks (#12050)
Signed-off-by: Joe Runde <Joseph.Runde@ibm.com>
2025-01-16 00:31:01 +08:00
maang-h
57e729e874
[Doc]: Update OpenAI-Compatible Server documents (#12082) 2025-01-15 16:07:45 +00:00
kewang-xlnx
de0526f668
[Misc][Quark] Upstream Quark format to VLLM (#10765)
Signed-off-by: kewang-xlnx <kewang@xilinx.com>
Signed-off-by: kewang2 <kewang2@amd.com>
Co-authored-by: kewang2 <kewang2@amd.com>
Co-authored-by: Michael Goin <michael@neuralmagic.com>
2025-01-15 11:05:15 -05:00
Yuan
5ecf3e0aaf
Misc: allow to use proxy in HTTPConnection (#12042)
Signed-off-by: Yuan Zhou <yuan.zhou@intel.com>
2025-01-15 13:16:40 +00:00
RunningLeon
97eb97b5a4
[Model]: Support internlm3 (#12037) 2025-01-15 11:35:17 +00:00
wangxiyuan
3adf0ffda8
[Platform] Do not raise error if _Backend is not found (#12023)
Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>
Signed-off-by: Mengqing Cao <cmq0113@163.com>
Co-authored-by: Mengqing Cao <cmq0113@163.com>
2025-01-15 10:14:15 +00:00
Keyun Tong
ad388d25a8
Type-fix: make execute_model output type optional (#12020) 2025-01-15 09:44:56 +00:00
Rahul Tuli
cbe94391eb
Fix: cases with empty sparsity config (#12057)
Signed-off-by: Rahul Tuli <rahul@neuralmagic.com>
2025-01-15 17:41:24 +08:00
Chen Zhang
994fc655b7
[V1][Prefix Cache] Move the logic of num_computed_tokens into KVCacheManager (#12003) 2025-01-15 07:55:30 +00:00
Kyle Sayers
3f9b7ab9f5
[Doc] Update examples to remove SparseAutoModelForCausalLM (#12062)
Signed-off-by: Kyle Sayers <kylesayrs@gmail.com>
2025-01-15 06:36:01 +00:00
youkaichao
ad34c0df0f
[core] platform agnostic executor via collective_rpc (#11256)
Signed-off-by: youkaichao <youkaichao@gmail.com>
2025-01-15 13:45:21 +08:00
Rui Qiao
f218f9c24d
[core] Turn off GPU communication overlap for Ray executor (#12051)
Signed-off-by: Rui Qiao <ruisearch42@gmail.com>
2025-01-15 05:19:55 +00:00
Elfie Guo
0794e7446e
[Misc] Add multipstep chunked-prefill support for FlashInfer (#10467) 2025-01-15 12:47:49 +08:00
Woosuk Kwon
b7ee940a82
[V1][BugFix] Fix edge case in VLM scheduling (#12065)
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
2025-01-14 20:21:28 -08:00
Shanshan Shen
9ddac56311
[Platform] move current_memory_usage() into platform (#11369)
Signed-off-by: Shanshan Shen <467638484@qq.com>
2025-01-15 03:38:25 +00:00
Konrad Zawora
1a51b9f872
[HPU][Bugfix] Don't use /dev/accel/accel0 for HPU autodetection in setup.py (#12046)
Signed-off-by: Konrad Zawora <kzawora@habana.ai>
2025-01-15 02:59:18 +00:00
Jee Jee Li
42f5e7c52a
[Kernel] Support MulAndSilu (#11624)
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
2025-01-15 02:29:53 +00:00
Jee Jee Li
a3a3ee4e6f
[Misc] Merge bitsandbytes_stacked_params_mapping and packed_modules_mapping (#11924)
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
2025-01-15 07:49:49 +08:00
maang-h
87054a57ab
[Doc]: Update the Json Example of the Engine Arguments document (#12045) 2025-01-14 17:03:04 +00:00
Harry Mellor
c9d6ff530b
Explain where the engine args go when using Docker (#12041)
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
2025-01-14 16:05:50 +00:00
Chen Zhang
a2d2acb4c8
[Bugfix][Kernel] Give unique name to BlockSparseFlashAttention (#12040)
Signed-off-by: Chen Zhang <zhangch99@outlook.com>
2025-01-14 15:45:05 +00:00
wangxiyuan
2e0e017610
[Platform] Add output for Attention Backend (#11981)
Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>
2025-01-14 13:27:04 +00:00
Chen Zhang
1f18adb245
[Kernel] Revert the API change of Attention.forward (#12038)
Signed-off-by: Chen Zhang <zhangch99@outlook.com>
2025-01-14 20:59:32 +08:00
Cyrus Leung
bb354e6b2d
[Bugfix] Fix various bugs in multi-modal processor (#12031)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
2025-01-14 12:16:11 +00:00
youkaichao
ff39141a49
[HPU][misc] add comments for explanation (#12034)
Signed-off-by: youkaichao <youkaichao@gmail.com>
2025-01-14 19:24:06 +08:00
TJian
8a1f938e6f
[Doc] Update Quantization Hardware Support Documentation (#12025)
Signed-off-by: tjtanaa <tunjian.tan@embeddedllm.com>
Co-authored-by: tjtanaa <tunjian.tan@embeddedllm.com>
2025-01-14 04:37:52 +00:00
Konrad Zawora
078da31903
[HPU][Bugfix] set_forward_context and CI test execution (#12014)
Signed-off-by: Konrad Zawora <kzawora@habana.ai>
2025-01-14 11:04:18 +08:00
Woosuk Kwon
1a401252b5
[Docs] Add Sky Computing Lab to project intro (#12019)
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
2025-01-13 17:24:36 -08:00
Steve Luo
f35ec461fc
[Bugfix] Fix deepseekv3 gate bias error (#12002)
Signed-off-by: mgoin <michael@neuralmagic.com>
Co-authored-by: mgoin <michael@neuralmagic.com>
2025-01-13 13:43:51 -07:00
Yikun Jiang
289b5191d5
[Doc] Fix build from source and installation link in README.md (#12013)
Signed-off-by: Yikun <yikunkero@gmail.com>
2025-01-13 17:23:59 +00:00
elijah
c6db21313c
bugfix: Fix signature mismatch in benchmark's get_tokenizer function (#11982)
Signed-off-by: elijah <f1renze.142857@gmail.com>
2025-01-13 15:22:07 +00:00