biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity
5,444 Commits 2 Branches 140 Tags
8958217ad5a6830c4d911e5f15e6eb791df337b6
Commit Graph

5444 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
Hiroaki Sugiyama
8958217ad5 [Bugfix] Fix use_cascade_attention handling for Alibi-based models on vllm/v1 (#15211) 
Signed-off-by: h-sugi <h.sugi@ieee.org>
Co-authored-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
 2025-03-27 22:29:29 +08:00
Cyrus Leung
ac5bc615b0 [Model] MiniCPM-V/O supports V1 (#15487) 
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
 2025-03-27 06:07:29 -07:00
Reid
8063dfc61a [Doc] update --system for transformers installation in docker doc (#15616) 
Signed-off-by: reidliu41 <reid201711@gmail.com>
Co-authored-by: reidliu41 <reid201711@gmail.com>
 2025-03-27 20:38:46 +08:00
Richard Zou
6278bc829e Fix incorrect filenames in vllm_compile_cache.py (#15494) 
Signed-off-by: <zou3519@gmail.com>
Signed-off-by: youkaichao <youkaichao@gmail.com>
Co-authored-by: youkaichao <youkaichao@gmail.com>
 2025-03-27 18:33:41 +08:00
wang.yuqi
3f532cb6a6 [Misc] Use model_redirect to redirect the model name to a local folder. (#14116) 2025-03-27 02:21:23 -07:00
Cyrus Leung
e6c9053f9e [Misc] Clean up scatter_patch_features (#15559) 
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
 2025-03-27 07:45:00 +00:00
Robert Shaw
43ed4143c4 [Quantization] Fp8 Channelwise Dynamic Per Token GroupedGEMM (#15587) 
Signed-off-by: ElizaWszola <eliza@neuralmagic.com>
Signed-off-by: ElizaWszola <ewszola@redhat.com>
Signed-off-by: rshaw@neuralmagic.com <robertgshaw2@gmail.com>
Co-authored-by: ElizaWszola <eliza@neuralmagic.com>
Co-authored-by: Lucas Wilkinson <wilkinson.lucas@gmail.com>
Co-authored-by: ElizaWszola <ewszola@redhat.com>
 2025-03-27 06:47:25 +00:00
Bella kira
f4c98b4d4c [Misc] Consolidate LRUCache implementations (#15481) 
Signed-off-by: Bella kira <2374035698@qq.com>
 2025-03-27 06:43:43 +00:00
Robert Shaw
e1e0fd7543 [TPU] Avoid Triton Import (#15589) 
Signed-off-by: rshaw@neuralmagic.com <robertgshaw2@gmail.com>
 2025-03-27 06:43:02 +00:00
Rui Qiao
df8d3d1287 [Misc] Restrict ray version dependency and update PP feature warning in V1 (#15556) 2025-03-27 06:21:07 +00:00
Chengji Yao
619d3de8bd [TPU] [V1] fix cases when max_num_reqs is set smaller than MIN_NUM_SEQS (#15583) 
Signed-off-by: Chengji Yao <chengjiyao@google.com>
 2025-03-26 22:46:26 -07:00
Gregory Shtrasberg
ecff8309a3 [ROCm] Env variable to trigger custom PA (#15557) 
Signed-off-by: Gregory Shtrasberg <Gregory.Shtrasberg@amd.com>
 2025-03-26 22:46:12 -07:00
Jerry Zhang
dcf2a590f5 Allow torchao quantization in SiglipMLP (#15575) 2025-03-26 22:45:51 -07:00
Cody Yu
54aa619459 [V1] Refactor num_computed_tokens logic (#15307) 
Signed-off-by: Cody Yu <hao.yu.cody@gmail.com>
Co-authored-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
 2025-03-27 04:54:36 +00:00
Mengqing Cao
fb22be5817 [moe][quant] add weight name case for offset (#15515) 
Signed-off-by: Mengqing Cao <cmq0113@163.com>
 2025-03-27 04:50:29 +00:00
Wei Zeng
7f301dd8ef [Doc] Update V1 user guide for fp8 kv cache support (#15585) 
Signed-off-by: weizeng <weizeng@roblox.com>
 2025-03-26 19:39:03 -07:00
Varun Sundar Rabindranath
8095341a01 [misc] LoRA: Remove unused long context test data (#15558) 
Signed-off-by: Varun Sundar Rabindranath <varun@neuralmagic.com>
Co-authored-by: Varun Sundar Rabindranath <varun@neuralmagic.com>
 2025-03-27 10:04:51 +08:00
Chenyaaang
69db16a46a add platform check back (#15578) 
Signed-off-by: Chenyaaang <llccyy1212@gmail.com>
 2025-03-27 01:50:27 +00:00
Michael Goin
ce78f9af4e Add automatic tpu label to mergify.yml (#15560) 2025-03-26 21:39:58 -04:00
ElizaWszola
9239bf718e [Kernel] CUTLASS grouped gemm fp8 MoE kernel (#13972) 
Signed-off-by: ElizaWszola <eliza@neuralmagic.com>
Signed-off-by: ElizaWszola <ewszola@redhat.com>
Co-authored-by: Lucas Wilkinson <wilkinson.lucas@gmail.com>
 2025-03-27 00:54:44 +00:00
Matthew Vine
7a6d45bc8a Support FIPS enabled machines with MD5 hashing (#15299) 
Signed-off-by: Matthew Vine <32849887+MattTheCuber@users.noreply.github.com>
 2025-03-26 20:19:46 -04:00
Chengji Yao
e74ff409e0 [TPU] support disabling xla compilation cache (#15567) 
Signed-off-by: Chengji Yao <chengjiyao@google.com>
 2025-03-27 00:09:28 +00:00
Wes
7a888271f5 Use Cache Hinting for fused_moe kernel (#15511) 2025-03-26 23:21:34 +00:00
Alexander Matveev
9d119a86ae [V1] TPU CI - Fix test_compilation.py (#15570) 
Signed-off-by: Alexander Matveev <amatveev@redhat.com>
 2025-03-26 21:51:54 +00:00
Alexander Matveev
b2e85e26f4 [V1] TPU - Revert to exponential padding by default (#15565) 
Signed-off-by: Alexander Matveev <amatveev@redhat.com>
 2025-03-26 21:35:05 +00:00
Alexei-V-Ivanov-AMD
dd8a29da99 Applying some fixes for K8s agents in CI (#15493) 
Signed-off-by: Alexei V. Ivanov <alexei.ivanov@amd.com>
 2025-03-26 20:35:11 +00:00
marko
27df5199d9 Support SHA256 as hash function in prefix caching (#15297) 
Signed-off-by: Marko Rosenmueller <5467316+dr75@users.noreply.github.com>
 2025-03-26 11:11:28 -07:00
Nick Hill
35fad35a48 [V1][Sampler] Faster top-k only implementation (#15478) 
Signed-off-by: Nick Hill <nhill@redhat.com>
 2025-03-26 10:56:47 -07:00
Aaron Pham
733e7c9e95 [Refactor] Remove unnecessary backend parameter in structured output interface (#15317) 
Signed-off-by: Aaron Pham <contact@aarnphm.xyz>
 2025-03-26 17:51:56 +00:00
Harry Mellor
0af4d764d6 Fix weight loading for some models in Transformers backend (#15544) 
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
 2025-03-26 10:17:53 -07:00
youkaichao
e64afa455c multi-node offline DP+EP example (#15484) 
Signed-off-by: youkaichao <youkaichao@gmail.com>
 2025-03-26 23:54:24 +08:00
Alex Brooks
1711b929b6 [Model] Add Reasoning Parser for Granite Models (#14202) 
Signed-off-by: Alex-Brooks <Alex.brooks@ibm.com>
Co-authored-by: Joe Runde <joe@joerun.de>
 2025-03-26 14:28:07 +00:00
Harry Mellor
c091c0a588 Improve validation of TP in Transformers backend (#15540) 
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
 2025-03-26 07:26:48 -07:00
cyyever
1aa162e030 Apply torchfix (#15532) 
Signed-off-by: cyy <cyyever@outlook.com>
 2025-03-26 12:09:06 +00:00
Harry Mellor
cf5c8f1686 Separate base model from TransformersModel (#15467) 
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Signed-off-by: Isotr0py <2037008807@qq.com>
Co-authored-by: Isotr0py <2037008807@qq.com>
Co-authored-by: Isotr0py <mozf@mail2.sysu.edu.cn>
 2025-03-26 18:13:38 +08:00
Reid
4ec2cee000 [Misc] improve example script output (#15528) 
Signed-off-by: reidliu41 <reid201711@gmail.com>
Co-authored-by: reidliu41 <reid201711@gmail.com>
 2025-03-26 10:12:47 +00:00
wwl2755
99f536f830 [Misc] Enhance warning information to user-defined chat template (#15408) 
Signed-off-by: wwl2755 <wangwenlong2755@gmail.com>
 2025-03-26 02:21:15 -07:00
vllmellm
5ebf66748b [FEAT][ROCm] Integrate Fused MoE Kernels from AITER (#14967) 
Signed-off-by: vllmellm <vllm.ellm@embeddedllm.com>
Signed-off-by: tjtanaa <tunjian.tan@embeddedllm.com>
Co-authored-by: tjtanaa <tunjian.tan@embeddedllm.com>
 2025-03-26 16:30:30 +08:00
Bryan Lu
781d056280 [Feature] Enhance EAGLE Architecture with Proper RMS Norms (#14990) 
Signed-off-by: Bryan Lu <yuzhelu@amazon.com>
Co-authored-by: Cyrus Leung <cyrus.tl.leung@gmail.com>
 2025-03-26 08:24:07 +00:00
daniel-salib
5aefd6ac31 Fix raw_request extraction in load_aware_call decorator (#15382) 
Signed-off-by: Daniel Salib <danielsalib@meta.com>
 2025-03-25 22:29:54 -07:00
Varun Sundar Rabindranath
6c663dfd5e [misc] LoRA - Skip LoRA kernels when not required (#15152) 
Signed-off-by: Varun Sundar Rabindranath <varun@neuralmagic.com>
Co-authored-by: Varun Sundar Rabindranath <varun@neuralmagic.com>
 2025-03-26 11:33:45 +08:00
Lucas Wilkinson
33437bc6e7 [BugFix] Fix nightly MLA failure (FA2 + MLA chunked prefill, i.e. V1, producing bad results) (#15492) 
Signed-off-by: LucasWilkinson <lwilkinson@neuralmagic.com>
 2025-03-25 20:33:22 -07:00
Tyler Michael Smith
23114d3364 [Misc] Warn about v0 in benchmark_paged_attn.py (#15495) 
Signed-off-by: Tyler Michael Smith <tyler@neuralmagic.com>
 2025-03-25 20:31:04 -07:00
Cyrus Leung
997c8811d6 [Model] Support multi-image for Molmo (#15438) 
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
 2025-03-26 11:26:33 +08:00
Harry Mellor
e42389f9d7 Transformers backend already supports V1 (#15463) 
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
 2025-03-25 20:26:16 -07:00
Varun Sundar Rabindranath
ff38f0a32c [CI/Build] LoRA: Delete long context tests (#15503) 
Signed-off-by: Varun Sundar Rabindranath <varun@neuralmagic.com>
Co-authored-by: Varun Sundar Rabindranath <varun@neuralmagic.com>
 2025-03-25 17:18:34 -07:00
Varun Sundar Rabindranath
a5cfbab3c8 [Core] LoRA: V1 Scheduler optimization (#15422) 
Signed-off-by: Varun Sundar Rabindranath <varun@neuralmagic.com>
Co-authored-by: Varun Sundar Rabindranath <varun@neuralmagic.com>
 2025-03-25 22:50:09 +00:00
Chenyaaang
ac3cd6e83c [core] add bucket padding to tpu_model_runner (#14995) 
Signed-off-by: Chenyaaang <llccyy1212@gmail.com>
Signed-off-by: rshaw@neuralmagic.com <robertgshaw2@gmail.com>
Co-authored-by: rshaw@neuralmagic.com <robertgshaw2@gmail.com>
 2025-03-25 17:27:22 -04:00
Lu Fang
082ab86f5f [V1] Support long_prefill_token_threshold in v1 scheduler (#15419) 
Signed-off-by: Lu Fang <lufang@fb.com>
 2025-03-25 14:22:26 -07:00
Nick Hill
6aa196c8dc [V1][Minor] Use SchedulerInterface type for engine scheduler field (#15499) 
Signed-off-by: Nick Hill <nhill@redhat.com>
 2025-03-25 14:21:36 -07:00