5112 Commits

Author SHA1 Message Date
Lasha Koroshinadze
e7767eccae Fix AudioFlamingo3/MusicFlamingo HF parity and RoTE handling (#37643)
Signed-off-by: Lasha <26011196+lashahub@users.noreply.github.com>
2026-03-23 10:29:07 +08:00
Wentao Ye
eaf4978621 [Test] Only Run MLA model when user explicitly set for batch invariance (#37719)
Signed-off-by: yewentao256 <zhyanwentao@126.com>
2026-03-22 09:09:12 -04:00
Andreas Karatzas
cd1242d82a [ROCm][CI] Stabilize ROCm speech-to-text translation test with lower min acc threshold (#37723)
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
2026-03-22 17:32:08 +08:00
Robert Shaw
4383f1532e [MoE] Move PF Methods to Folder (#35927) 2026-03-22 02:42:59 -06:00
Andreas Karatzas
6ecba840d7 [ROCm][CI] get_cu_count was renamed to num_compute_units in #35042 (#37764)
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
2026-03-22 16:02:21 +08:00
Andreas Karatzas
3b06c55c78 [ROCm][CI] Fix MEGA_AOT_ARTIFACT fallback when PyTorch < 2.10.0 lacks AOT support (#37763)
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
2026-03-22 16:02:03 +08:00
Andreas Karatzas
c862481c02 [CI] Skip ISAAC multimodal tests due to broken upstream HF model weights (#37781)
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
2026-03-22 13:23:32 +08:00
Andreas Karatzas
c86b17cfe6 [ROCm][CI] Add large_gpu_mark to test_max_tokens_none for ROCm (#37717)
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
2026-03-22 12:25:16 +08:00
Andreas Karatzas
66f927f205 [Bugfix] Fix pooling non-determinism from pinned prompt_lens aliasing (#37775)
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
2026-03-22 03:22:24 +00:00
Robert Shaw
6b2fa3a762 [MoE] Move FlashInfer CuteDSL experts into fused_moe/experts/ (#37759)
Signed-off-by: Robert Shaw <robertgshaw2@gmail.com>
2026-03-21 19:15:16 -04:00
Robert Shaw
eeee5b262d [Quantization][Deprecation] Remove PTPC FP8 (#32700)
Signed-off-by: Robert Shaw <robshaw@redhat.com>
Co-authored-by: Robert Shaw <robshaw@redhat.com>
2026-03-21 22:10:16 +00:00
Brandon Pelfrey
80b70884eb Add tensor IPC transfer mechanism for multimodal data (#32104)
Signed-off-by: Brandon Pelfrey <bpelfrey@nvidia.com>
Signed-off-by: Brandon Pelfrey <brandonpelfrey@gmail.com>
Signed-off-by: Nick Hill <nickhill123@gmail.com>
Co-authored-by: Nick Hill <nickhill123@gmail.com>
2026-03-21 20:10:20 +00:00
Francesco Fusco
298e510848 [Hybrid] calling get_mamba_groups() once at MambaCopyBuffers.create() (#37318)
Signed-off-by: Francesco Fusco <ffu@zurich.ibm.com>
2026-03-21 09:29:43 +00:00
Andreas Karatzas
0d50fa1db6 [ROCm][CI] Mark gemma3 as large GPU test to avoid OOM on MI250 (#37610)
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
2026-03-21 12:57:25 +08:00
Simon Mo
1fa1e53a73 Revert "[compile] Initialize passes at VllmBackend init" (#37733) 2026-03-20 21:35:49 -07:00
Andreas Karatzas
3ffa52009f [ROCm][CI] Guard CudaPlatform/RocmPlatform imports to fix test collection on cross-platform builds (#37617)
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
2026-03-21 11:58:58 +08:00
Yongye Zhu
87bd91892f [MoE Refactor] Mxfp4 oracle rebased (#37128)
Signed-off-by: Yongye Zhu <zyy1102000@gmail.com>
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-21 03:37:04 +00:00
Isotr0py
c7f98b4d0a [Frontend] Remove librosa from audio dependency (#37058)
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
2026-03-21 11:36:15 +08:00
Santino Ramos
85f671b8e1 [Model Runner V2] Support Streaming Inputs (#37028)
Signed-off-by: Santino Ramos <elsantinoramos@gmail.com>
2026-03-20 20:42:25 +00:00
Vadim Gimpelson
4f16ebbbd3 [Bugfix] Disable monolithic TRTLLM MoE for Renormalize routing (#37591) (#37605)
Signed-off-by: Vadim Gimpelson <vadim.gimpelson@gmail.com>
2026-03-20 12:19:26 -07:00
Angela Yi
12fd17eb51 [compile] Initialize passes at VllmBackend init (#35216)
Signed-off-by: angelayi <yiangela7@gmail.com>
2026-03-20 11:40:33 -07:00
Lucas Wilkinson
e1d85e5c24 [Attention] Support distinguishing between short extends and decodes (#37303)
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
2026-03-20 10:49:36 -07:00
Xin Yang
d0532bf38d [Perf] Eliminate redundant SparseMatrix creation in gpt_oss_triton_kernels (#37683)
Signed-off-by: Xin Yang <xyangx@amazon.com>
2026-03-20 11:28:41 -06:00
Andreas Karatzas
fb4e8bf442 [ROCm][CI] Fix accuracy for llama-nemotron-vl pooling tests (#37613)
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
2026-03-20 10:16:59 -07:00
Harry Mellor
6ade4bc5a5 Fix various config related issues for Transformers v5 (#37681)
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
2026-03-20 16:30:12 +00:00
Zhengxu Chen
2e089b96a8 [compile] Add compiled artifact counter for VLLM_USE_MEGA_AOT_ARTIFACT=1. (#37589)
Signed-off-by: zhxchen17 <zhxchen17@fb.com>
2026-03-20 16:22:46 +00:00
Zhengxu Chen
c0f5fae601 [compile] Fix aot test failures with torch 2.12. (#37604)
Signed-off-by: zhxchen17 <zhxchen17@fb.com>
2026-03-20 16:06:29 +00:00
L.B.R.
1779c09898 [ROCm] Enable wvSplitK skinny GEMM kernel for RDNA4/gfx1x decode (#34709)
Signed-off-by: L.B.R. <lbr@mmonad.com>
Co-authored-by: L.B.R. <lbr@mmonad.com>
2026-03-20 10:11:23 -05:00
Ilya Boytsov
8b6c6b9505 [Model] Add LFM2-ColBERT-350M support (#37528)
Signed-off-by: Ilya Boytsov <ilyaboytsov1805@gmail.com>
2026-03-20 14:57:57 +00:00
Harry Mellor
9f6d9dd371 Fix attribute error in isaac_patch_hf_runner (#37685)
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
2026-03-20 14:49:40 +00:00
Flora Feng
b4c1aef21c [Refactor] Relocate tests from tests/v1/entrypoints/ to tests/entrypoints/ (#37500)
Signed-off-by: sfeng33 <4florafeng@gmail.com>
2026-03-20 02:50:34 -07:00
Flora Feng
6050b93bed [Refactor] Move serve entrypoint tests under tests/entrypoints/serve/ (#37595)
Signed-off-by: sfeng33 <4florafeng@gmail.com>
2026-03-20 02:10:47 -07:00
Andreas Karatzas
5a4a179591 [ROCm][CI] Fix granite_speech test for gfx90a by selecting compatible attention backend (#37611)
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
2026-03-20 17:07:26 +08:00
Andreas Karatzas
9cfd4ebb5e [ROCm][CI] Update GSM8K eval config to use fp8-and-mixed models list (#37619)
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
2026-03-20 17:06:53 +08:00
wang.yuqi
ed359c497a [Model] Deprecate the score task (this will not affect users). (#37537)
Signed-off-by: wang.yuqi <yuqi.wang@daocloud.io>
2026-03-20 08:07:56 +00:00
Flora Feng
e2d1c8b5e8 [Refactor] Relocate entrypoint tests to match serving code structure (#37593)
Signed-off-by: sfeng33 <4florafeng@gmail.com>
2026-03-20 05:31:23 +00:00
Flora Feng
9040151fe1 [V0 Deprecation] Deprecate --disable-frontend-multiprocessing (#37612)
Signed-off-by: sfeng33 <4florafeng@gmail.com>
2026-03-20 11:31:43 +08:00
Jee Jee Li
8fbe3f303f [Bugfix][LoRA] Fix Qwen35 LoRA (#36976)
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
2026-03-20 11:09:32 +08:00
Xiao
ea2c148fa7 [compile][graph_partition]Add tensor size handling (#36038)
Signed-off-by: Xiao Fu <xiaofu@meta.com>
2026-03-19 19:55:25 -07:00
tianshu-Michael-yu
269bf46d99 fix: disambiguate multimodal prefix cache keys (#36708)
Signed-off-by: tianshu.yu <tianshuyu.formal@gmail.com>
2026-03-20 10:33:20 +08:00
Flora Feng
be12afd284 [Bugfix] Fix Deepseekv32 tool parser when stream interval > 1 (#36056) 2026-03-19 19:51:25 -04:00
rasmith
98ff042917 [CI][BugFix][AMD] Don't set VLLM_ROCM_USE_AITER anymore in test_rocm_aiter_topk since its not necessary (#36996)
Signed-off-by: Randall Smith <Randall.Smith@amd.com>
2026-03-20 07:12:45 +08:00
Laith Sakka
112944fab9 test Qwen/Qwen3-4B-Instruct-2507 for unbacked (#36064)
Signed-off-by: Laith Sakka <lsakka@meta.com>
2026-03-19 17:28:45 -04:00
Andreas Karatzas
040a505ff5 [ROCm][CI] Cleaning and restructuring amd-ci legacy pipeline (#34839)
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
2026-03-19 14:30:58 -05:00
Ifta khairul Alam Adil
104605cbf2 Remove deprecated reasoning_content message field(part-2) (#37480)
Signed-off-by: JartX <sagformas@epdcenter.es>
Signed-off-by: Ifta Khairul Alam Adil <ikaadil007@gmail.com>
Signed-off-by: Netanel Haber <58652339+netanel-haber@users.noreply.github.com>
Signed-off-by: yewentao256 <zhyanwentao@126.com>
Signed-off-by: Philip Ottesen <phiott256@gmail.com>
Signed-off-by: Woosuk Kwon <woosuk@inferact.ai>
Signed-off-by: Michael Goin <mgoin64@gmail.com>
Signed-off-by: Giancarlo Delfin <gdelfin@inferact.ai>
Signed-off-by: Andy Lo <andy@mistral.ai>
Signed-off-by: Thillai Chithambaram <thillaichithambaram.a@gmail.com>
Signed-off-by: sihao.li <sihao.li@intel.com>
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Co-authored-by: JartX <sagformas@epdcenter.es>
Co-authored-by: Netanel Haber <58652339+netanel-haber@users.noreply.github.com>
Co-authored-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com>
Co-authored-by: Philip Ottesen <phiott256@gmail.com>
Co-authored-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
Co-authored-by: Michael Goin <mgoin64@gmail.com>
Co-authored-by: Giancarlo Delfin <32987265+TheEpicDolphin@users.noreply.github.com>
Co-authored-by: Andy Lo <andy@mistral.ai>
Co-authored-by: Thillai Chithambaram <79466435+thillai-c@users.noreply.github.com>
Co-authored-by: sihao_li <165983188+1643661061leo@users.noreply.github.com>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
2026-03-19 15:20:08 +00:00
DorBernsohn
c63ca2b2e6 [Bugfix] Add Kimi-K2.5 reasoning/tool parser aliases and tool_call_id support (#37438)
Signed-off-by: DorBernsohn <dor.bernsohn@gmail.com>
2026-03-19 21:08:00 +08:00
Cyrus Leung
765e461065 [Bugfix] Fix Nemotron Parse loading (#37407)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
2026-03-19 09:55:29 +00:00
zhanqiuhu
d49f273144 [SSM/Mamba] Follow-up: N-1 prefill for P/D disaggregation (#37310) 2026-03-19 08:22:00 +01:00
Flora Feng
b21d384304 [Refactor] Relocate endpoint tests to mirror serving code directory structure (#37504)
Signed-off-by: sfeng33 <4florafeng@gmail.com>
2026-03-19 07:19:36 +00:00
Sage Moore
c32a58cc2a [EPLB] Simplify EPLB rearrange by only returning one map (#36267)
Signed-off-by: Sage Moore <sage@neuralmagic.com>
Co-authored-by: Tyler Michael Smith <tyler@neuralmagic.com>
2026-03-18 20:34:00 -04:00