|
2ded1b24e7
|
[KV Connector][Mooncake] Apply SWA lookup mask before hashing/key build (#47317)
Signed-off-by: Zhewen Li <zhewenli@inferact.ai>
Co-authored-by: Zhewen Li <zhewenli@inferact.ai>
Co-authored-by: Codex <codex@openai.com>
Co-authored-by: Claude <noreply@anthropic.com>
|
2026-07-09 19:51:23 +00:00 |
|
|
|
b0dec2a11b
|
[ROCM][DSV32][Perf][MTP] Enable UNIFORM_BATCH CG mode in rocm_aiter_mla_sparse (#45149)
Signed-off-by: Teemu Virolainen <teemu.virolainen@amd.com>
Co-authored-by: TJian <tunjian.tan@embeddedllm.com>
Co-authored-by: Andreas Karatzas <akaratza@amd.com>
|
2026-07-09 14:35:10 -05:00 |
|
|
|
ff8d3488f2
|
[Bugfix][MRV2] Reset num_accepted_tokens on add_request in all modes (#48132)
Signed-off-by: Nick Hill <nickhill123@gmail.com>
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
|
2026-07-09 18:17:11 +00:00 |
|
|
weishuandGitHub
|
2285cfca46
|
[KVConnector] MultiConnector: give every sub-connector the request's real blocks in update_state_after_alloc (#46865)
Signed-off-by: deng451e <838677410@qq.com>
|
2026-07-09 11:10:39 -07:00 |
|
|
|
e08a915146
|
[Bugfix] Preserve tensor causal metadata for grouped attention (#48135)
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
Co-authored-by: Codex <codex@openai.com>
|
2026-07-09 17:57:53 +00:00 |
|
|
Charlie FuandGitHub
|
67e7ea8977
|
[ROCm][CI] Set all timeout_in_minutes to 180 (#48146)
Signed-off-by: charlifu <charlifu@amd.com>
|
2026-07-09 17:52:26 +00:00 |
|
|
|
429f405748
|
[Bugfix] Guard CUDA-only rms_norm_per_block_quant in FUSED_OPS for non-CUDA builds (#47296)
Signed-off-by: Tsvika Shapira <tsvika@moonmath.ai>
Co-authored-by: Claude <noreply@anthropic.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
2026-07-09 10:10:53 -04:00 |
|
|
Brandon PelfreyandGitHub
|
753c5039f0
|
Pin PyNvVideoCodec to tested 2.0.4 wheel (#48056)
|
2026-07-09 07:07:50 -07:00 |
|
|
|
299d2b5655
|
[CI] Annotate built Docker image tags on the Buildkite build page (#48101)
Signed-off-by: khluu <khluu000@gmail.com>
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
|
2026-07-09 22:02:40 +08:00 |
|
|
|
85b3a7264b
|
[Bugfix][Model Runner V2] Order uniform decodes first so spec decodes aren't misclassified as prefills (#47381)
Signed-off-by: Woosuk Kwon <woosuk@inferact.ai>
Signed-off-by: Nick Hill <nickhill123@gmail.com>
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
Co-authored-by: Nick Hill <nickhill123@gmail.com>
|
2026-07-09 14:26:27 +01:00 |
|
|
Harry MellorandGitHub
|
b83be00cdd
|
Migrate Olmo and Olmo2 to the Transformers modeling backend (#48100)
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
|
2026-07-09 05:00:23 -07:00 |
|
|
|
412414d8e0
|
Remove PersimmonForCausalLM and FuyuForCausalLM model architectures (#48096)
Signed-off-by: Xianbao QIAN <xianbao.qian@gmail.com>
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Signed-off-by: Cyrus Leung <tlleungac@connect.ust.hk>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>
|
2026-07-09 04:59:08 -07:00 |
|
|
|
ae6170f874
|
[P/D][Bugfix] Fix PD async KV load lookahead handling for MTP spec decode (#46694)
Signed-off-by: chaunceyjiang <chaunceyjiang@gmail.com>
Co-authored-by: Nick Hill <nickhill123@gmail.com>
|
2026-07-09 10:01:22 +00:00 |
|
|
|
e87521626f
|
Sanitize server file paths from validation error responses (#46415)
Signed-off-by: muhammadfawaz1 <135441198+muhammadfawaz1@users.noreply.github.com>
Co-authored-by: Mahad Durrani <114791389+mahadrehmann@users.noreply.github.com>
|
2026-07-09 17:46:29 +08:00 |
|
|
|
1cd75b3dd4
|
[Bugfix] Fix race condition in KVBlockZeroer (#48085)
Signed-off-by: Benjamin Chislett <bchislett@nvidia.com>
Signed-off-by: Benjamin Chislett <chislett.ben@gmail.com>
Co-authored-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com>
|
2026-07-09 09:18:19 +00:00 |
|
|
|
0206f10871
|
Add Intel XPU Docker release pipeline (#47880)
Signed-off-by: wenjun.liu <wenjun.liu@intel.com>
Signed-off-by: jun,du <jun.du@intel.com>
Co-authored-by: jun,du <jun.du@intel.com>
Co-authored-by: Kunshang Ji <kunshang.ji@intel.com>
|
2026-07-09 01:13:51 -07:00 |
|
|
|
ab7961a14a
|
Remove TeleChatForCausalLM (#47989)
Signed-off-by: Xianbao QIAN <xianbao.qian@gmail.com>
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
|
2026-07-09 00:34:54 -07:00 |
|
|
|
a07765c6bd
|
[Bugfix] Fix Qwen3-ASR transcription streaming postprocessing (#42478)
Signed-off-by: JooHo Lee <BWAAEEEK@users.noreply.github.com>
Signed-off-by: JooHo Lee <jooho414@gmail.com>
Co-authored-by: JooHo Lee <BWAAEEEK@users.noreply.github.com>
|
2026-07-09 00:33:27 -07:00 |
|
|
Li, JiangandGitHub
|
1171467e91
|
[CPU] Fix Qwen-Next SSM type for AMX GDN (#48073)
Signed-off-by: jiang1.li <jiang1.li@intel.com>
|
2026-07-09 15:09:31 +08:00 |
|
|
ChaunceyandGitHub
|
529af88842
|
[KV Offloading] Add free block iterator for CPU offload scheduling (#47849)
Signed-off-by: chaunceyjiang <chaunceyjiang@gmail.com>
|
2026-07-09 06:59:54 +00:00 |
|
|
Chaojun ZhangandGitHub
|
b8c7c86533
|
[XPU][LoRA] Fix torch.compile DEVICE_LOST by avoiding view-mutation in LoRA shrink (#47944)
Signed-off-by: Chaojun Zhang <chaojun.zhang@intel.com>
|
2026-07-09 06:08:30 +00:00 |
|
|
|
2c17d33f42
|
[Bugfix][ROCm] Change AttentionCGSuppoort in TritonMLA to UNIFORM_SINGLE_TOKEN_DECODE (#47144)
Signed-off-by: Dino Music <Dino.Music@amd.com>
Co-authored-by: Andreas Karatzas <akaratza@amd.com>
|
2026-07-08 21:09:42 -05:00 |
|
|
|
bc44f9feb7
|
[ROCm][CI][MoE] Fix double-transpose of fused w3 expert weights (#47874)
Signed-off-by: stefankoncarevic <stefan.koncarevic@amd.com>
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
Co-authored-by: Andreas Karatzas <akaratza@amd.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
2026-07-08 16:59:28 -07:00 |
|
|
|
7802c20c4e
|
[KVConnector][NIXL] Support pipeline-parallel prefill in push mode (#45880)
Signed-off-by: zixi-qi <zixi@inferact.ai>
Co-authored-by: Nick Hill <nickhill123@gmail.com>
|
2026-07-08 16:49:23 -07:00 |
|
|
|
95d6d6f4bb
|
[Bugfix] Use int8 workspace for FlashInfer MLA decode (#48046)
Signed-off-by: Nick Hill <nickhill123@gmail.com>
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
|
2026-07-08 23:39:40 +00:00 |
|
|
Harry MellorandGitHub
|
56da398dac
|
Fix embed scaling + CUDA graphs in Transformers modelling backend (#48010)
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
|
2026-07-09 00:14:33 +01:00 |
|
|
Andreas KaratzasandGitHub
|
26831949b4
|
[ROCm] Fix pooling startup workspace lock (#47912)
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
|
2026-07-08 17:59:50 -05:00 |
|
|
|
6cf7b26bd4
|
[docs] Fix the docs build (#48008)
Signed-off-by: Martin Hickey <martin.hickey@ie.ibm.com>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
|
2026-07-08 15:47:22 -07:00 |
|
|
Roberto L. CastroandGitHub
|
5f85975624
|
[Feat] Add runtime monitor for post-warmup TileLang compilation (#46718)
Signed-off-by: LopezCastroRoberto <rocastro@redhat.com>
Signed-off-by: Roberto L. Castro <38211239+LopezCastroRoberto@users.noreply.github.com>
|
2026-07-08 22:11:28 +00:00 |
|
|
|
dcdd756d75
|
[CI] GSM8K eval integration test for KV offloading (#46893)
Signed-off-by: Tyler Michael Smith <tyler@tylermsmith.com>
Signed-off-by: Tyler Michael Smith <tlrmchlsmth@gmail.com>
Signed-off-by: Itay Etelis <itay.etelis@ibm.com>
Signed-off-by: Itay Etelis <92247226+Etelis@users.noreply.github.com>
Signed-off-by: Or Ozeri <oro@il.ibm.com>
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Co-authored-by: Itay Etelis <92247226+Etelis@users.noreply.github.com>
Co-authored-by: Itay Etelis <itay.etelis@ibm.com>
Co-authored-by: Or Ozeri <oro@il.ibm.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
2026-07-08 17:59:48 -04:00 |
|
|
Thien TranandGitHub
|
0d2f4e7c9c
|
Allow FlashInfer A2A backends for TRTLLM FP8 MoE Modular (#46661)
Signed-off-by: Thien Tran <gau.nernst@yahoo.com.sg>
|
2026-07-08 14:58:39 -07:00 |
|
|
djramicandGitHub
|
49abadaedb
|
[ROCm][Bugfix] Fix empty-tensor .max() crash in AITER FA (#47894)
Signed-off-by: Djordje Ramic <djoramic@amd.com>
|
2026-07-08 16:58:36 -05:00 |
|
|
Kaihang JiangandGitHub
|
089e412878
|
[Perf] Integrate TRTLLM BF16 MoE Modular Kernel (#45182)
Signed-off-by: Kaihang Jiang <kaihangj@login-lyris02.lyris.clusters.nvidia.com>
|
2026-07-09 01:36:14 +04:00 |
|
|
Nick HillandGitHub
|
a5d19cbb95
|
[Core] Move MRV1 late_interaction_runner.py out of MRV2 subtree (#48014)
Signed-off-by: Nick Hill <nickhill123@gmail.com>
|
2026-07-08 18:30:11 +00:00 |
|
|
Chris LeonardandGitHub
|
8347c6e6e1
|
updated flash_attn GIT_TAG to point to torch Stable ABI FA3 commit (#47995)
Signed-off-by: Chris Leonard <chleonar@redhat.com>
|
2026-07-08 10:56:29 -07:00 |
|
|
|
b2cf70ea3a
|
[CI] BugFix Eval Small Models Distributed test for DiffusionGemma (#47980)
Signed-off-by: Markov Ilya <markovilya19@gmail.com>
Co-authored-by: Markov Ilya <markovilya19@gmail.com>
|
2026-07-08 17:00:56 +00:00 |
|
|
almayneandGitHub
|
d1f1d86797
|
[Bugfix] Re-enable benchmarking of librispeech dataset. (#47033)
Signed-off-by: Anna Mayne <anna.mayne@arm.com>
|
2026-07-08 16:19:26 +00:00 |
|
|
shawnandGitHub
|
f05603fa28
|
[Bugfix][DCP] Cast LSE to fp32 in a2a combine to fix bf16 bitcast crash (#47801)
Signed-off-by: Shawn Tsai <shawnyht@gmail.com>
|
2026-07-08 11:41:26 -04:00 |
|
|
|
c2ecd0f888
|
Fix FlashAttention MLA prefill V unpadding (#42642)
Signed-off-by: Martin Vit <martin@voipmonitor.org>
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
Co-authored-by: Matthew Bonanni <mbonanni@redhat.com>
|
2026-07-08 15:22:20 +00:00 |
|
|
|
0d12618e98
|
[Spec Decode] Support hybrid (SWA + full attention) DFlash drafters (#47914)
Signed-off-by: mgoin <mgoin64@gmail.com>
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
|
2026-07-08 11:12:45 -04:00 |
|
|
Tyler Michael SmithandGitHub
|
68b4a1d582
|
Fix NVML capability lookup for visible devices (#47892)
Signed-off-by: Tyler Michael Smith <tlrmchlsmth@gmail.com>
|
2026-07-08 09:07:44 -04:00 |
|
|
|
572b25b03e
|
[Bug] Fix Batched DeepGEMM (#47884)
Signed-off-by: Robert Shaw <robertgshaw2-redhat@dgx-b200-02.mgmt.accl-001.lab.rdu2.dc.redhat.com>
Co-authored-by: Robert Shaw <robertgshaw2-redhat@dgx-b200-02.mgmt.accl-001.lab.rdu2.dc.redhat.com>
Co-authored-by: Claude <noreply@anthropic.com>
|
2026-07-08 09:05:03 -04:00 |
|
|
|
9f2b3b093c
|
Improvement of Docker image build for IBM Power using prebuilt wheels from IBM published devpi index (#46017)
Signed-off-by: vivek sharma <vivsharm@redhat.com>
Signed-off-by: puneetsharma21 <puneet.sharma21@ibm.com>
Signed-off-by: Puneet Sharma <puneet.sharma21@ibm.com>
Co-authored-by: vivek sharma <vivsharm@redhat.com>
Co-authored-by: Puneet Sharma <puneet.sharma21@ibm.com>
Co-authored-by: depthfirst-app[bot] <184448029+depthfirst-app[bot]@users.noreply.github.com>
|
2026-07-08 13:01:14 +00:00 |
|
|
|
cd0de48d08
|
[Bugfix][V1] Free out-of-window blocks on the processed-token basis under async scheduling (#47728)
Signed-off-by: Saddss <28726669061@qq.com>
Signed-off-by: Nick Hill <nickhill123@gmail.com>
Signed-off-by: Yifan Qiao <yifanqiao@inferact.ai>
Co-authored-by: Yifan Qiao <yifanqiao@inferact.ai>
Co-authored-by: Saddss <28726669061@qq.com>
Co-authored-by: Nick Hill <nickhill123@gmail.com>
|
2026-07-08 13:34:19 +01:00 |
|
|
rasmithandGitHub
|
934eeaecfb
|
[CI/Build][BugFix][The Rock] Fix get_ssm_device_name to return sanitized, usable filename (#47781)
Signed-off-by: Randall Smith <Randall.Smith@amd.com>
|
2026-07-08 12:12:54 +00:00 |
|
|
Bugen ZhaoandGitHub
|
2cae98dfa5
|
[Rust Frontend] Handle continue_final_message with renderer sentinel (#47844)
Signed-off-by: Bugen Zhao <i@bugenzhao.com>
|
2026-07-08 12:57:04 +01:00 |
|
|
|
db39d60010
|
Add tuned selective_state_update float32 config for AMD Instinct MI355 (#47943)
Signed-off-by: vanshbhatia-amd <210711135+vanshbhatia-amd@users.noreply.github.com>
Co-authored-by: vanshbhatia-amd <210711135+vanshbhatia-amd@users.noreply.github.com>
|
2026-07-08 11:41:26 +00:00 |
|
|
|
a1ab51afb6
|
[Bugfix] Allocate HY V3 expert_bias in float32 to prevent silent downcasting (#47797)
Signed-off-by: 辰言 <oncwnuIWp30GguOyJ615Fqj8H-yc@git.weixin.qq.com>
Signed-off-by: Jee Jee Li <jeejeelee@inferact.ai>
Co-authored-by: 辰言 <oncwnuIWp30GguOyJ615Fqj8H-yc@git.weixin.qq.com>
Co-authored-by: Jee Jee Li <jeejeelee@inferact.ai>
Co-authored-by: Jee Jee Li <pandaleefree@gmail.com>
|
2026-07-08 11:25:53 +00:00 |
|
|
Thien TranandGitHub
|
e7b3853bac
|
Remove router weight upcast for DSv2-related models (#47970)
Signed-off-by: Thien Tran <gau.nernst@yahoo.com.sg>
|
2026-07-08 11:19:10 +00:00 |
|
|
|
eeaf23107f
|
[ROCm] Add tuned selective_state_update float32 config for AMD Instinct MI300X (#47947)
Signed-off-by: vanshbhatia-amd <210711135+vanshbhatia-amd@users.noreply.github.com>
Co-authored-by: vanshbhatia-amd <210711135+vanshbhatia-amd@users.noreply.github.com>
|
2026-07-08 11:09:02 +00:00 |
|