Commit Graph

5001 Commits

Author SHA1 Message Date
Andreas Karatzas
b9cdc85207 [ROCm][CI] Fix Whisper translation test attention backend selection (#38508)
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
2026-03-31 13:21:49 +08:00
SandishKumarHN
bcc6f67447 [Bugfix] Use null block (0) for padded block table entries (#35431)
Signed-off-by: SandishKumarHN <sandish@fb.com>
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
Co-authored-by: Lucas Wilkinson <LucasWilkinson@users.noreply.github.com>
Co-authored-by: Matthew Bonanni <mbonanni@redhat.com>
2026-03-30 14:02:51 -07:00
Micah Williamson
d9c7db18da [ROCm][CI] Pin test_hybrid test to TRITON_ATTN on ROCm (#38381)
Signed-off-by: Micah Williamson <micah.williamson@amd.com>
2026-03-30 20:26:46 +00:00
Ilya Markov
12701e8af2 [EPLB] Optmize eplb mapping and record in router for prefill (#36261)
Signed-off-by: ilmarkov <markovilya197@gmail.com>
2026-03-30 19:48:33 +00:00
Benjamin Chislett
494636b29d [Feat][Spec Decode] DFlash (#36847)
Signed-off-by: Benjamin Chislett <bchislett@nvidia.com>
2026-03-30 15:03:15 -04:00
Chendi.Xue
3b1dbaad4e [HMA]Fix corner case when hybrid page_size can not be evenly divided issue (blk_size=64,tp=4) (#37467)
Signed-off-by: Chendi Xue <chendi.xue@intel.com>
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
Signed-off-by: Chendi.Xue <chendi.xue@intel.com>
Co-authored-by: Matthew Bonanni <mbonanni@redhat.com>
Co-authored-by: Nicolò Lucchesi <nlucches@redhat.com>
2026-03-30 16:47:30 +00:00
Johnny
b4a2f3ac36 [NVIDIA] Bugfix NVFP4 DGX Spark and RTX50 (#38423)
Signed-off-by: johnnynunez <johnnynuca14@gmail.com>
Signed-off-by: Johnny <johnnynuca14@gmail.com>
2026-03-30 09:36:18 -07:00
roikoren755
8e6293e838 [Mamba] Add stochastic rounding support (#35753)
Signed-off-by: Roi Koren <roik@nvidia.com>
2026-03-30 12:33:49 -04:00
Hongxia Yang
dbdd9ae067 [ROCm][Bugfix] fix exception related to trust_remote_code for MiniMax-M2.1-MXFP4 (#37698)
Signed-off-by: Hongxia Yang <hongxiay.yang@amd.com>
Co-authored-by: Hongxia Yang <hongxiay.yang@amd.com>
2026-03-30 15:49:23 +00:00
Matthias Gehre
e8b055a5ac [Bugfix] Handle ParallelLMHead in compressed-tensors get_quant_method (#37291)
Signed-off-by: Matthias Gehre <matthias.gehre@amd.com>
Co-authored-by: Michael Goin <mgoin64@gmail.com>
2026-03-30 07:30:52 -07:00
Andreas Karatzas
677424c7ac [Core][CI] Add opt-in media URL caching via VLLM_MEDIA_CACHE (#37123)
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
2026-03-30 04:58:53 -07:00
Collin McCarthy
1031c84c36 Fix ambiguous num_blocks for hybrid attn mamba (#37236)
Signed-off-by: Collin McCarthy <cmccarthy@nvidia.com>
Signed-off-by: Netanel Haber <58652339+netanel-haber@users.noreply.github.com>
Co-authored-by: Netanel Haber <58652339+netanel-haber@users.noreply.github.com>
2026-03-30 11:09:45 +00:00
aliialsaeedii
7e76af14fa [Bugfix][Frontend] Return 400 for corrupt/truncated image inputs instead of 500 (#38253)
Signed-off-by: aliialsaeedii <ali.al-saeedi@nscale.com>
2026-03-30 10:26:46 +00:00
yzong-rh
3683fe6c06 [Bugfix] Fix shared-object aliasing in n>1 streaming with tool calls (#38158)
Signed-off-by: Yifan Zong <yzong@redhat.com>
Signed-off-by: Yifan <yzong@redhat.com>
Co-authored-by: Chauncey <chaunceyjiang@gmail.com>
2026-03-30 10:12:13 +00:00
Nicolò Lucchesi
cc06b4e86b [Mamba][Bugfix] Raise on insufficient cache blocks instead of silently capping cudagraph sizes (#38270)
Signed-off-by: NickLucche <nlucches@redhat.com>
2026-03-30 09:41:50 +00:00
haosdent
a08b7733fd [CI] Fix SPLADE pooler test broken by #38139 (#38495)
Signed-off-by: haosdent <haosdent@gmail.com>
2026-03-30 07:48:33 +00:00
Juan Pérez de Algaba
57861ae48d (security) Fix SSRF in batch runner download_bytes_from_url (#38482)
Signed-off-by: jperezde <jperezde@redhat.com>
2026-03-30 07:10:01 +00:00
Andreas Karatzas
bea23536f6 [CI] Add temperature=0.0, reduce max_tokens, and add debug prints to audio_in_video tests (#38492)
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
2026-03-30 05:36:45 +00:00
Stanislav Kirillov
a6db99ba02 [Bugfix] Support multi-type params parsing for DeepSeek v3.2 (#33703)
Signed-off-by: Stanislav Kirillov <stas@nebius.com>
Co-authored-by: Stanislav Kirillov <stas@nebius.com>
Co-authored-by: Chauncey <chaunceyjiang@gmail.com>
2026-03-30 04:07:28 +00:00
Andreas Karatzas
4f2ed5fddb [ROCm][CI] Enable hybrid chunked prefill test (#38317)
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
2026-03-30 10:30:26 +08:00
Kyle Sayers
d28d86e8a3 [QeRL] Fix online quantized reloading (#38442)
Signed-off-by: Kyle Sayers <kylesayrs@gmail.com>
2026-03-29 14:56:41 -06:00
Wentao Ye
995dea1354 [Perf] Remove redundant device copies for CPU-only pooling token IDs, 48.9% E2E throughput improvement (#38139)
Signed-off-by: yewentao256 <zhyanwentao@126.com>
2026-03-29 18:12:50 +00:00
Andreas Karatzas
43cc5138e5 [ROCm][CI] Fix cross-attention dispatch for encoder-decoder models (#38450)
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
2026-03-28 22:08:03 -07:00
haosdent
d39b8daf5f [Feature] Add Qwen3-ForcedAligner support via token classification pooling (#35367)
Signed-off-by: haosdent <haosdent@gmail.com>
2026-03-29 00:27:52 +00:00
Walter Beller-Morales
fafca38adc [BugFix][Frontend] apply task instruction as system prompt in cohere v2/embed (#38362)
Signed-off-by: walterbm <walter.beller.morales@gmail.com>
2026-03-28 18:30:54 +00:00
haosdent
b2bc736b12 [CI] Fix Ernie4.5-VL initialization test (#38429)
Signed-off-by: haosdent <haosdent@gmail.com>
2026-03-28 22:43:24 +08:00
Bvicii
bda3eda82d [Bugfix] Disallow renderer_num_workers > 1 with mm processor cache (#38418)
Signed-off-by: Bvicii <yizhanhuang2002@gmail.com>
2026-03-28 06:32:52 -07:00
yzong-rh
6dad4c5722 [Test] Fix flaky race condition in test_abort_final_step (#38414)
Signed-off-by: Yifan <yzong@redhat.com>
2026-03-28 09:06:56 +00:00
Nicolò Lucchesi
44a6528028 [CI] Skip failing test (#38369)
Signed-off-by: NickLucche <nlucches@redhat.com>
2026-03-27 13:25:19 -07:00
Kyle Sayers
648edcf729 [QeRL] Compose online quantization with quantized reloading (#38032)
Signed-off-by: Kyle Sayers <kylesayrs@gmail.com>
2026-03-27 13:22:33 -07:00
Jonas M. Kübler
98e7f223b9 enable skipping of SW attention layers when using FP8 KV cache (#33695)
Signed-off-by: Jonas Kuebler <kuebj@amazon.com>
2026-03-27 07:25:02 -06:00
Juan Pérez de Algaba
b111f8a61f fix(security): Add VLLM_MAX_N_SEQUENCES environment variable and enforce limit (#37952)
Signed-off-by: jperezde <jperezde@redhat.com>
Signed-off-by: Russell Bryant <rbryant@redhat.com>
Co-authored-by: Russell Bryant <rbryant@redhat.com>
2026-03-27 09:02:10 -04:00
Sage Moore
497e234d38 [EPLB] Cleanup the transfer logic for the various eplb maps (#34520)
Signed-off-by: Sage Moore <sagmoore@redhat.com>
Signed-off-by: Sage Moore <sage@neuralmagic.com>
2026-03-27 10:18:46 +01:00
dtc
6287e7fa20 [P/D] Mooncake: Add unit tests and minor fixes for mooncake connector (#36946)
Signed-off-by: Tianchen Ding <dtcccc@linux.alibaba.com>
2026-03-27 09:26:40 +01:00
Flora Feng
aee4c14689 [Bugfix] Fix Hermes tool parser when stream interval > 1 (#38168)
Signed-off-by: sfeng33 <4florafeng@gmail.com>
2026-03-27 14:42:26 +08:00
Li, Jiang
becaed6ec8 [CPU] Support CT W4A16 on CPU MP kernel (#38219)
Signed-off-by: jiang1.li <jiang1.li@intel.com>
2026-03-27 14:15:28 +08:00
Or Ozeri
7cc302dd87 [kv_offload+HMA][7/N]: Support register_kv_caches for hybrid models (#37853)
Signed-off-by: Or Ozeri <oro@il.ibm.com>
2026-03-27 08:38:33 +03:00
Bvicii
999dfc1622 [Bugfix] Offload blocking tokenizer ops to shared thread pool to unblock event loop (#34789)
Signed-off-by: Bvicii <yizhanhuang2002@gmail.com>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>
2026-03-26 22:17:00 -07:00
Giancarlo Delfin
c32e97602d [Model Runner V2] Enable forcing a specific acceptance rate during rejection sampling (#38045)
Signed-off-by: Giancarlo Delfin <gdelfin@inferact.ai>
2026-03-26 13:38:12 -07:00
Andreas Karatzas
9c3ae04bfe [ROCm][CI] Add LM Eval Qwen3.5 Models test for MI355 (#38155)
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
2026-03-26 16:51:18 +00:00
Divakar Verma
b9dbc5c4ab [Mamba][APC] Add test case to compare apc outputs (#34977)
Signed-off-by: Divakar Verma <divakar.verma@amd.com>
2026-03-26 16:40:35 +00:00
Andreas Karatzas
bdc1719eb9 [ROCm][CI] Fix AITER state leak in shared_fused_moe_routed_transform test (#38137)
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
2026-03-26 09:26:46 -07:00
Zhewen Li
be1a85b7a2 Revert "[MoE Kernel] Flashinfer nvfp4 cutedsl moe kernel integration" (#38050) (#38169)
Co-authored-by: Zhewen Li <zhewenli@inferact.ai>
2026-03-26 07:59:09 -07:00
Cyrus Leung
2e225f7bd2 [Renderer] Consolidate factory methods (#38218)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
2026-03-26 12:19:22 +00:00
wang.yuqi
dcdc145893 [CI] Reorganize scoring tests (#38207)
Signed-off-by: wang.yuqi <yuqi.wang@daocloud.io>
2026-03-26 12:07:01 +00:00
Andreas Karatzas
f2d16207c7 [ROCm][CI] Fix flaky GPTQ compile correctness test (#38161)
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
2026-03-26 19:57:00 +08:00
Andreas Karatzas
37a83007fe [ROCm][CI] Fix wvSplitKrc mock argument order in test_rocm_unquantized_gemm (#38167)
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
2026-03-26 19:54:59 +08:00
Wentao Ye
bf5eec638d [Refactor] Remove unused utils (#38153)
Signed-off-by: yewentao256 <zhyanwentao@126.com>
2026-03-26 17:08:19 +08:00
Vadim Gimpelson
52069012fe [Bugfix] Fix DeepGemm E8M0 accuracy degradation for Qwen3.5 FP8 on Blackwell (#38083)
Signed-off-by: Vadim Gimpelson <vadim.gimpelson@gmail.com>
2026-03-26 01:21:47 -07:00
Matej Rojec
2908094567 Add /v1/chat/completions/batch endpoint for batched chat completions (#38011)
Signed-off-by: Matej Rojec <64556640+MatejRojec@users.noreply.github.com>
2026-03-26 12:13:33 +08:00