 Matej SirovatkaandGitHub
|
b07ec92faa
|
[Bugfix] Make shared NVFP4 MoE scales writable (#49489)
Signed-off-by: S1ro1 <matej.sirovatka@gmail.com>
|
2026-07-22 19:17:53 -07:00 |
|
|
Nick HillandGitHub
|
229e01e9e1
|
[BugFix] Handle per-group prefix-hit divergence for hybrid models with KV connector (#48425)
|
2026-07-22 17:19:11 -07:00 |
|
|
Summer YangandGitHub
|
f3a920a076
|
[Core][DSV4] Compact MXFP4 indexer KV cache and packed group overlays (#48993)
|
2026-07-22 16:58:44 -07:00 |
|
|
|
149daf0d72
|
[Bugfix] Exclude location-derived path vars from torch.compile cache factors (#47573)
Signed-off-by: Nils Matteson <nilsmatteson@icloud.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
2026-07-22 16:56:09 -07:00 |
|
|
Nick HillandGitHub
|
910cc8543a
|
[Bugfix] Restore gather_and_maybe_dequant_cache OOB guard (#49427)
Signed-off-by: Nick Hill <nickhill123@gmail.com>
|
2026-07-22 13:47:37 -07:00 |
|
|
Nick HillandGitHub
|
431934522b
|
[CI] Fix stale/fragile untethered kernels-root tests (#49423)
Signed-off-by: Nick Hill <nickhill123@gmail.com>
|
2026-07-22 14:43:07 -06:00 |
|
|
|
3de4b2bf3c
|
[Bugfix][Parser] Fix special tokens (EOS/BOS) leaking into reasoning content (#48748)
Signed-off-by: Ben Browning <56071+bbrowning@users.noreply.github.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
2026-07-22 16:10:55 -04:00 |
|
|
|
b44311b6ef
|
[CI] stabilize GDN prefill CuTeDSL test (#49388)
Signed-off-by: Thien Tran <gau.nernst@yahoo.com.sg>
Co-authored-by: Codex <noreply@openai.com>
|
2026-07-22 09:03:46 -07:00 |
|
|
Wentao YeandGitHub
|
37e370fe93
|
[DSv4 Perf] Skip empty c128 kernel launch, around 2x kernel performance improvement. (#48957)
Signed-off-by: yewentao256 <zhyanwentao@126.com>
|
2026-07-22 10:55:20 -04:00 |
|
|
wang.yuqiandGitHub
|
61c9ef986a
|
[Frontend] Parallelize preprocessing within the same request for pooling models online serving. (#49153)
Signed-off-by: wang.yuqi <yuqi.wang@daocloud.io>
|
2026-07-22 10:56:23 +00:00 |
|
|
Andreas KaratzasandGitHub
|
16aca639b7
|
[ROCm] Upgrade NIXL and UCX (#49251)
Signed-off-by: Andreas Karatzas <Andreas.Karatzas@amd.com>
|
2026-07-21 22:30:02 -05:00 |
|
|
|
060b5f61dc
|
[Bugfix][Attention] Ignore empty MLA context chunks during merge (#49294)
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
Co-authored-by: OpenAI Codex <codex@openai.com>
|
2026-07-22 02:23:48 +00:00 |
|
|
|
ec59c1579f
|
[MoE Refactor] Migrate MoeWNA16Method quantization method over to using the new MK oracle scheme. (#44120)
Signed-off-by: Bill Nell <bnell@redhat.com>
Co-authored-by: Claude <noreply@anthropic.com>
Co-authored-by: mgoin <mgoin64@gmail.com>
|
2026-07-21 19:20:30 -07:00 |
|
|
Isotr0pyandGitHub
|
1750e443f2
|
[Misc] Move PyNvVideoCodec stuff out of gpu worker (#49322)
Signed-off-by: Isotr0py <Isotr0py@outlook.com>
|
2026-07-22 10:11:56 +08:00 |
|
|
|
ba18929079
|
[Bugfix][SpecDecode] Scope MTP completeness checks outside bucketed updates (#49178)
Signed-off-by: aoshen02 <aoshen02@users.noreply.github.com>
Co-authored-by: aoshen02 <aoshen02@users.noreply.github.com>
|
2026-07-21 18:56:39 -07:00 |
|
|
|
0500ca6a58
|
[CI][Bugfix] Fix ROCm FP8 KV cache dtype in attention backend test (#49380)
Signed-off-by: pei.zhang <pei.zhang@amd.com>
Co-authored-by: Claude <noreply@anthropic.com>
|
2026-07-22 01:34:49 +00:00 |
|
|
|
a1c15bcb0f
|
[CI][Bugfix] Fix and wire streaming-input tests (#49356)
Signed-off-by: Nick Hill <nickhill123@gmail.com>
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
|
2026-07-22 00:35:23 +00:00 |
|
|
stefankoncarevicandGitHub
|
05781e21dd
|
[ROCm][CI] Fix order-dependent failure in test_flash_attn_accepts_handled_fp8_variants (MI355) (#49329)
Signed-off-by: Stefan Koncarevic <Stefan.Koncarevic@amd.com>
|
2026-07-21 18:54:33 -05:00 |
|
|
gnovackandGitHub
|
85f638a2b8
|
skip cudagraph/DP padding in topk (#48979)
Signed-off-by: gnovack <novackgm@gmail.com>
|
2026-07-21 15:20:30 -07:00 |
|
|
|
a7d00ec051
|
[Bugfix] DFlash fc sized wrong when num_target_layers != num_hidden_layers (#48524)
Signed-off-by: mgoin <mgoin64@gmail.com>
Co-authored-by: Codex <noreply@openai.com>
|
2026-07-21 14:42:52 -07:00 |
|
|
Michael GoinandGitHub
|
b8fb56d970
|
[CI] Add gemma-4-E4B-it-assistant to CI gsm8k for GemmaMTP (#49243)
Signed-off-by: mgoin <mgoin64@gmail.com>
|
2026-07-21 16:51:04 -04:00 |
|
|
|
60d443f738
|
[CI/Build][The Rock][BugFix] Use fork method in test_multiproc_executor_multi_node for py 3.14 compat and fix test_multiproc_executor_shutdown_cleanup (#48655)
Signed-off-by: Randall Smith <Randall.Smith@amd.com>
Co-authored-by: Andreas Karatzas <akaratza@amd.com>
|
2026-07-21 15:40:29 -05:00 |
|
|
|
1dca300653
|
[CI] Fix and wire encoder/manager cudagraph unit tests (#49339)
Signed-off-by: Nick Hill <nickhill123@gmail.com>
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
|
2026-07-21 20:41:16 +01:00 |
|
|
Flora FengandGitHub
|
fca252d59e
|
[CI][Bugfix] Reduce max_model_len in OOT embedding test to fix KV-cache OOM on small GPUs (#49351)
Signed-off-by: sfeng33 <4florafeng@gmail.com>
|
2026-07-21 15:00:06 -04:00 |
|
|
|
de6ec294ef
|
[Bugfix] Fix DSA crash under breakable piecewise cudagraphs (#49302)
Signed-off-by: Nick Hill <nickhill123@gmail.com>
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
|
2026-07-21 18:28:13 +01:00 |
|
|
stefankoncarevicandGitHub
|
61e10f0116
|
[ROCm][CI] Fix AITER MLA fp8 decode metadata regression test (#48845)
Signed-off-by: Stefan Koncarevic <Stefan.Koncarevic@amd.com>
|
2026-07-21 12:19:45 -05:00 |
|
|
|
47f1b47a73
|
Ci/add laguna xs gsm8k (#49241)
Signed-off-by: Joe Rowell <joerowell4@gmail.com>
Signed-off-by: mgoin <mgoin64@gmail.com>
Co-authored-by: Joe Rowell <joerowell4@gmail.com>
|
2026-07-21 11:30:42 -04:00 |
|
|
|
5812e1a66b
|
[Test] Add DeepSeek MTP parallel-load tests (#41653)
Signed-off-by: Stefano Castagnetta <scastagnetta@nvidia.com>
Co-authored-by: Benjamin Chislett <bchislett@nvidia.com>
|
2026-07-21 10:38:20 -04:00 |
|
|
|
8950394e0a
|
[Bugfix] Prefix-cache metrics double-counted when a KV connector defers requests (#48860)
Signed-off-by: Seiji Eicher <58963096+eicherseiji@users.noreply.github.com>
Signed-off-by: Seiji Eicher <seiji@anyscale.com>
Signed-off-by: Nick Hill <nickhill123@gmail.com>
Co-authored-by: Lixi Zhang <muxixibbb@gmail.com>
Co-authored-by: harjothkhara <harjoth.khara@gmail.com>
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
Co-authored-by: Nick Hill <nickhill123@gmail.com>
|
2026-07-21 15:02:03 +01:00 |
|
|
|
f890e1dbe2
|
[BugFix] Set graph_pool_id before FULL CUDA graph capture in ModelRunner V2 (#48843)
Signed-off-by: Markov Ilya <markovilya19@gmail.com>
Co-authored-by: Markov Ilya <markovilya19@gmail.com>
|
2026-07-21 08:59:26 -04:00 |
|
|
bastefaniakandGitHub
|
4d30c510ce
|
[bugfix] Fix Cosmos3 Edge checkpoint weights filtering, video loading, prompt expansion (#49190)
Signed-off-by: Bartosz Stefaniak <bstefaniak@nvidia.com>
|
2026-07-21 17:18:36 +08:00 |
|
|
|
6700813f86
|
[3/N][KV-Cache Layout Refactor] Standardize Mamba cache; drop get_transfer_cache_regions (#44456)
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
Co-authored-by: Claude <noreply@anthropic.com>
Co-authored-by: OpenAI Codex <codex@openai.com>
|
2026-07-21 09:16:15 +00:00 |
|
|
Nicolò LucchesiandGitHub
|
7a98c7a392
|
[Misc] Remove old now unsupported max_num_partial_prefills and max_long_partial_prefills (#49244)
Signed-off-by: NickLucche <nicolo.lucchesi@mistral.ai>
|
2026-07-21 08:52:52 +00:00 |
|
|
|
1134545b6f
|
Revert "[Sampler] Stop upcasting logits to fp32 in apply_sampling_params" (#48641) (#49033)
Co-authored-by: vllm-agent <vllm-agent@users.noreply.github.com>
|
2026-07-21 09:36:45 +01:00 |
|
|
|
d9aa35161d
|
Update BGE-M3 token expectations for leading spaces (#49269)
Signed-off-by: aoshen02 <aoshen02@users.noreply.github.com>
Co-authored-by: aoshen02 <aoshen02@users.noreply.github.com>
Co-authored-by: Codex <noreply@openai.com>
|
2026-07-21 03:49:17 +00:00 |
|
|
|
6bcda970fd
|
[CI][NIXL] Isolate concurrent engine internal ports (#49129)
Signed-off-by: Andreas Karatzas <Andreas.Karatzas@amd.com>
Co-authored-by: OpenAI Codex <noreply@openai.com>
|
2026-07-20 22:28:11 -05:00 |
|
|
ChaunceyandGitHub
|
94ed0bf4e0
|
[Bugfix][KV Offloading] Handle queued request aborts without allocated KV blocks (#49146)
Signed-off-by: chaunceyjiang <chaunceyjiang@gmail.com>
|
2026-07-21 11:16:26 +08:00 |
|
|
Simon MoandGitHub
|
72d16aee15
|
[CI] Exercise FA3 FP8 attention on SM90 (#49231)
Signed-off-by: Simon Mo <simon@inferact.ai>
|
2026-07-21 10:26:55 +08:00 |
|
|
|
2e2e626b40
|
[Bugfix] Count per-group blocks in get_max_concurrency_for_kv_cache_config (#48317)
Signed-off-by: David Orman <ormandj@corenode.com>
Co-authored-by: Luke Alonso <lalonso@gmail.com>
Co-authored-by: Martin Vit <martin@voipmonitor.org>
Co-authored-by: Claude <noreply@anthropic.com>
Co-authored-by: Yifan Qiao <yifanqiao@inferact.ai>
|
2026-07-21 00:29:10 +00:00 |
|
|
|
2396a61108
|
[Attention][MLA][DCP] Query replication for MLA decode (DeepSeek-V2/R1 + Kimi-K2.5) (#45964)
Signed-off-by: Sungsoo Ha <sungsooh@nvidia.com>
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Co-authored-by: Lucas Wilkinson <lwilkins@redhat.com>
Co-authored-by: Matthew Bonanni <mbonanni@redhat.com>
|
2026-07-20 23:51:27 +00:00 |
|
|
|
97a668152b
|
[RL Infra][FlashInfer] Enable router replay output from FlashInfer monolithic MoE kernel (#44214)
Signed-off-by: Xuanyu Zhang <xuanyu.zhang@mistral.ai>
Co-authored-by: Claude <noreply@anthropic.com>
Co-authored-by: aoshen02 <aoshen@inferact.ai>
Co-authored-by: OpenAI Codex <noreply@openai.com>
|
2026-07-20 16:45:10 -07:00 |
|
|
|
58b2012aa2
|
[copy of #45208] CuMem slept-L1 fragmentation accounting (#49208)
Signed-off-by: haosdent <haosdent@gmail.com>
Signed-off-by: Justin Wood <justin.m.wood@me.com>
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
Co-authored-by: haosdent <haosdent@gmail.com>
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Co-authored-by: Justin Wood <jwood@me.com>
|
2026-07-20 23:08:11 +00:00 |
|
|
Charlie FuandGitHub
|
5feb3950e5
|
[ROCm][CI] fix test_rocm_quick_reduce.py (#49234)
Signed-off-by: charlifu <charlifu@amd.com>
|
2026-07-20 16:39:33 -05:00 |
|
|
|
4ec199b66a
|
[Bugfix][Spec-Decode] Populate draft seq_lens_cpu_upper_bound for spec-decode attention metadata (#44492)
Signed-off-by: Oxana Korzh <okorzh@amd.com>
Signed-off-by: okorzh-amd <okorzh-amd@users.noreply.github.com>
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
Co-authored-by: okorzh-amd <okorzh-amd@users.noreply.github.com>
Co-authored-by: Matthew Bonanni <mbonanni@redhat.com>
|
2026-07-20 20:50:58 +00:00 |
|
|
|
7ca017778f
|
[Feat][Perf] Add new warmup infrastructure for JITs (#47451)
Signed-off-by: LopezCastroRoberto <rocastro@redhat.com>
Signed-off-by: Roberto L. Castro <38211239+LopezCastroRoberto@users.noreply.github.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
2026-07-20 13:21:55 -07:00 |
|
|
|
fbfe58133d
|
[Bugfix][KV Offload] Preserve reachable tails for hybrid SWA groups (#48911)
Signed-off-by: Colton Ottley <colton@ottleyengineering.com>
Co-authored-by: Colton Ottley <colton@ottleyengineering.com>
Co-authored-by: Or Ozeri <oro@il.ibm.com>
|
2026-07-20 22:12:36 +03:00 |
|
|
|
9dd62d80ab
|
Cosmos3 FP8 ModelOpt/Diffusers remapping (#48952)
Signed-off-by: Wojciech Kutak <wkutak@nvidia.com>
Signed-off-by: wkutak <wkutak@nvidia.com>
Signed-off-by: Isotr0py <Isotr0py@outlook.com>
Co-authored-by: Isotr0py <Isotr0py@outlook.com>
Co-authored-by: Roger Wang <hey@rogerw.io>
|
2026-07-20 11:31:48 -07:00 |
|
|
|
bd091079cb
|
[Attention] FlashAttention 4 SM100 FP8 kv cache support (#42569)
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
2026-07-20 10:53:27 -07:00 |
|
|
Isotr0pyandGitHub
|
15cb8e140d
|
[Multimodal] Allow keeping original image mode for ImageIO (#49159)
Signed-off-by: Isotr0py <Isotr0py@outlook.com>
|
2026-07-20 13:42:45 +00:00 |
|
|
|
f007cceb42
|
[KV Offload] Support self-describing KV events with TieringOffloadingSpec (#48679)
Signed-off-by: Change72 <changg@nvidia.com>
Co-authored-by: OpenAI Codex <codex@openai.com>
|
2026-07-20 16:41:58 +03:00 |
|