5398 Commits

Author SHA1 Message Date
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
Nicolò Lucchesi
a0dd7dcd49
[TPU][V1] Fix Sampler recompilation (#15309)
Signed-off-by: NickLucche <nlucches@redhat.com>
2025-03-25 16:43:54 -04:00
Maximilien de Bayser
e977c11111
Add workaround for shared field_names in pydantic model class (#13925)
Signed-off-by: Max de Bayser <mbayser@br.ibm.com>
2025-03-25 20:31:08 +00:00
Joe Runde
5f063a80bd
[bugfix] add supports_v1 platform interface (#15417)
Signed-off-by: Joe Runde <Joseph.Runde@ibm.com>
2025-03-25 15:00:32 -04:00
Antonio Gómez
5d8e1c9279
[Bugfix] Support triton==3.3.0+git95326d9f for RTX 5090 (Unsloth + vLLM compatibility) (#15471)
Co-authored-by: ServerAI <ai@exc-mad-ai.com>
2025-03-25 17:59:25 +00:00
yarongmu-google
0a049c7d86
[CI/Build] Add tests for the V1 tpu_model_runner. (#14843)
Signed-off-by: Yarong Mu <ymu@google.com>
2025-03-25 12:27:16 -04:00
youkaichao
d0cfec7ab9
[bugfix] fix inductor cache on max_position_embeddings (#15436)
Signed-off-by: youkaichao <youkaichao@gmail.com>
2025-03-25 07:05:39 -07:00
Szymon Ożóg
a608160027
[Kernel] Fix conflicting macro names for gguf kernels (#15456)
Signed-off-by: SzymonOzog <szymon.ozog@gmail.com>
2025-03-25 13:50:49 +00:00
Cyrus Leung
3f04a7fbf2
[Doc] Update V1 user guide for multi-modality (#15460)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
2025-03-25 11:01:58 +00:00
Cyrus Leung
5994430b84
[Misc] Remove redundant num_embeds (#15443)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
2025-03-25 18:27:57 +08:00
Cyrus Leung
a9e879b316
[Misc] Clean up MiniCPM-V/O code (#15337)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
2025-03-25 10:22:52 +00:00
Md. Shafi Hussain
3e2f37a69a
Dockerfile.ppc64le changes to move to UBI (#15402)
Signed-off-by: Md. Shafi Hussain <Md.Shafi.Hussain@ibm.com>
2025-03-25 10:15:14 +00:00
Thien Tran
4f044b1d67
[Kernel][CPU] CPU MLA (#14744)
Signed-off-by: Thien Tran <gau.nernst@yahoo.com.sg>
2025-03-25 09:34:59 +00:00
Siyuan Liu
4157f563b4
[Hardware][TPU][Bugfix] Fix v1 mp profiler (#15409)
Signed-off-by: Siyuan Liu <lsiyuan@google.com>
2025-03-25 01:43:00 -07:00
Lu Fang
051da7efe3
Fix CUDA kernel index data type in vllm/csrc/quantization/gptq_marlin/awq_marlin_repack.cu +10 (#15160)
Signed-off-by: Lu Fang <lufang@fb.com>
Co-authored-by: Richard Barnes <rbarnes@meta.com>
2025-03-25 15:36:45 +08:00
Woosuk Kwon
25f560a62c
[V1][Spec Decode] Update target_logits in place for rejection sampling (#15427)
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
v0.8.2
2025-03-24 21:04:41 -07:00
Russell Bryant
a09ad90a72
[V1] guidance backend for structured output + auto fallback mode (#14779)
Signed-off-by: Russell Bryant <rbryant@redhat.com>
Co-authored-by: Loc Huynh <jc1da.3011@gmail.com>
Co-authored-by: Michal Moskal <michal@moskal.me>
2025-03-24 21:02:33 -07:00
Chauncey
10b34e36b9
[Bugfix] Fixed the issue of not being able to input video and image simultaneously (#15387)
Signed-off-by: chaunceyjiang <chaunceyjiang@gmail.com>
2025-03-25 03:48:08 +00:00
Tyler Michael Smith
b5269db959
Revert "Fix non-contiguous input passed to Marlin kernel (#15319)" (#15398) 2025-03-24 20:43:51 -07:00
Jee Jee Li
6db94571d7
[Misc] Remove LoRA log (#15388)
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
2025-03-24 20:43:48 -07:00
Harry Mellor
97cfa65df7
Add pipeline parallel support to TransformersModel (#12832)
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>
2025-03-25 10:41:45 +08:00
Woosuk Kwon
911c8eb000
[Minor][Spec Decode] Remove compiled_softmax (#15416)
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
2025-03-24 19:09:04 -07:00
Woosuk Kwon
ebcebeeb6b
[V1][Spec Decode] Enable spec decode for top-p & top-k sampling (#15063)
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
2025-03-24 17:16:46 -07:00
Gregory Shtrasberg
f533b5837f
[ROCm][Kernel] MoE weights padding (#14454)
Signed-off-by: Gregory Shtrasberg <Gregory.Shtrasberg@amd.com>
Signed-off-by: charlifu <charlifu@amd.com>
Co-authored-by: charlifu <charlifu@amd.com>
2025-03-24 23:45:30 +00:00
Gregory Shtrasberg
8279201ce6
[Build] Cython compilation support fix (#14296)
Signed-off-by: Gregory Shtrasberg <Gregory.Shtrasberg@amd.com>
2025-03-24 23:37:54 +00:00
Siyuan Liu
23fdab00a8
[Hardware][TPU] Skip failed compilation test (#15421)
Signed-off-by: Siyuan Liu <lsiyuan@google.com>
2025-03-24 23:28:57 +00:00
Nick Hill
623e2ed29f
[BugFix][V1] Quick fix for min_tokens with multiple EOS (#15407)
Signed-off-by: Nick Hill <nhill@redhat.com>
2025-03-24 15:58:59 -07:00
Nick Hill
9d72daf4ce
[V1][Perf] Simpler request output queues (#15156)
Signed-off-by: Nick Hill <nhill@redhat.com>
Signed-off-by: rshaw@neuralmagic.com <robertgshaw2@gmail.com>
Co-authored-by: rshaw@neuralmagic.com <robertgshaw2@gmail.com>
2025-03-24 22:44:08 +00:00
Cyrus Leung
6dd55af6c9
[Doc] Update docs on handling OOM (#15357)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
Signed-off-by: Roger Wang <ywang@roblox.com>
Co-authored-by: Roger Wang <ywang@roblox.com>
2025-03-24 14:29:34 -07:00
Yuan Tang
3eb08ed9b1
[DOC] Add Kubernetes deployment guide with CPUs (#14865) 2025-03-24 10:48:43 -07:00
liuzhenwei
5eeadc2642
[Hardware][Gaudi][Feature] Enable Dynamic MoE for Mixtral (#12303)
Signed-off-by: zhenwei <zhenweiliu@habana.ai>
2025-03-24 09:48:40 -07:00
Nick Hill
3aee6573dc
[V1] Aggregate chunked prompt logprobs in model runner (#14875)
Signed-off-by: Nick Hill <nhill@redhat.com>
2025-03-24 12:27:57 -04:00
Yi Liu
9cc645141d
[MISC] Refine no available block debug msg (#15076)
Signed-off-by: Yi Liu <yiliu4@habana.ai>
Signed-off-by: yiliu30 <yi4.liu@intel.com>
Co-authored-by: Yi Liu <yiliu4@habana.ai>
2025-03-25 00:01:10 +08:00
Chen1022
0893567db9
[V1][Minor] fix comments (#15392)
Signed-off-by: chenjincong <chenjincong@baidu.com>
Signed-off-by: Chen-0210 <chenjincong11@gmail.com>
Co-authored-by: chenjincong <chenjincong@baidu.com>
2025-03-24 08:45:32 -07:00
Russell Bryant
8abe69b499
[Core] Don't force uppercase for VLLM_LOGGING_LEVEL (#15306)
Signed-off-by: Russell Bryant <rbryant@redhat.com>
2025-03-24 08:27:30 -07:00
Manish Sethi
761702fd19
[Core] Integrate fastsafetensors loader for loading model weights (#10647)
Signed-off-by: Manish Sethi <Manish.sethi1@ibm.com>
2025-03-24 08:08:02 -07:00
youkaichao
9606d572ed
[distributed] fix dp group (#15355)
Signed-off-by: youkaichao <youkaichao@gmail.com>
2025-03-24 14:54:27 +00:00
Cyrus Leung
cbcdf2c609
[Bugfix] Fix chat template loading (#15143)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
Signed-off-by: Roger Wang <ywang@roblox.com>
Co-authored-by: chaunceyjiang <chaunceyjiang@gmail.com>
Co-authored-by: Roger Wang <ywang@roblox.com>
2025-03-24 13:50:09 +00:00
Russell Bryant
038de04d7b
Fix zmq IPv6 URL format error (#15341)
Signed-off-by: Russell Bryant <rbryant@redhat.com>
2025-03-24 09:30:41 -04:00
Jinzhen Lin
6b3cc75be0
[Kernel] allow non-contiguous input for marlin kernel (#14658)
Signed-off-by: Jinzhen Lin <linjinzhen@hotmail.com>
2025-03-24 09:21:33 -04:00
Simon Mo
7ffcccfa5c
Revert "[CI/Build] Use uv python for docker rather than ppa:deadsnakess/ppa (#13569)" (#15377)
Signed-off-by: simon-mo <simon.mo@hey.com>
2025-03-24 05:53:10 -07:00
sfbemerk
cc8accfd53
[Misc] Update guided decoding logs to debug (#15310)
Signed-off-by: Benjamin Merkel <benjamin.merkel@tngtech.com>
Co-authored-by: Benjamin Merkel <benjamin.merkel@tngtech.com>
2025-03-24 04:25:20 -07:00
ℍ𝕠𝕝𝕝𝕠𝕨 𝕄𝕒𝕟
948ab03e7e
[Bugfix][V1] Avoid importing PreTrainedModel (#15366)
Signed-off-by: Hollow Man <hollowman@opensuse.org>
2025-03-24 10:33:12 +00:00
Rui Qiao
5797fb97e9
[Misc] Remove ignore_reinit_error for ray.init() (#15373) 2025-03-24 07:41:53 +00:00
Jee Jee Li
3892e58ad7
[Misc] Upgrade BNB version (#15183) 2025-03-24 05:51:42 +00:00
Qubitium-ModelCloud
d20e261199
Fix non-contiguous input passed to Marlin kernel (#15319) 2025-03-24 03:09:44 +00:00
Luka Govedič
f622dbcf39
[Fix] [torch.compile] Improve UUID system for custom passes (#15249)
Signed-off-by: luka <luka@neuralmagic.com>
2025-03-24 01:54:07 +00:00