|
d490b98162
|
[Core] Avoid mixed length specdec batches via padding (#45237)
Signed-off-by: Yiliu Dong <91178480+qianlihuang@users.noreply.github.com>
Signed-off-by: Nick Hill <nickhill123@gmail.com>
Co-authored-by: Nick Hill <nickhill123@gmail.com>
Co-authored-by: Jade Zheng <zheng.shoujian@outlook.com>
Co-authored-by: Giancarlo Delfin <gdelfin@inferact.ai>
Co-authored-by: Zijing Liu <liuzijing2014@gmail.com>
|
2026-06-25 08:34:44 -07:00 |
|
|
haoyangli0109andGitHub
|
1744adc256
|
[ROCM] [Communication] Add INT3 quantization method for quickreduce (#45666)
Signed-off-by: Haoyang Li <lihaoyang0109@gmail.com>
|
2026-06-25 15:14:15 +00:00 |
|
|
|
9bfd878a48
|
[MoE] [MoE Refactor] Add moe kernel oracle abc 37753 (#43461)
Signed-off-by: Qiuyang Yue <yueqiuyang1389@gmail.com>
Signed-off-by: qyYue1389 <yueqiuyang1389@gmail.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
2026-06-25 09:34:03 -04:00 |
|
|
|
15be78732b
|
[NIXL][Mamba] Add Mamba1 support to NIXL P/D disaggregation (#45019)
Signed-off-by: Josephasafg <ajgard7@gmail.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
2026-06-25 05:50:41 -07:00 |
|
|
|
72adb20a6a
|
[Model] Remove AquilaForCausalLM, AquilaModel (#46605)
Signed-off-by: Xianbao QIAN <xianbao.qian@gmail.com>
Co-authored-by: Claude <noreply@anthropic.com>
|
2026-06-25 08:08:26 +00:00 |
|
|
Bugen ZhaoandGitHub
|
4d3b4b9b01
|
[Rust Frontend] Make ToolParserOutput a seq of ToolParserEvent to preserve order (#46584)
Signed-off-by: Bugen Zhao <i@bugenzhao.com>
|
2026-06-25 06:27:07 +00:00 |
|
|
Jeff (Junze) MaandGitHub
|
36fd7e8b86
|
[SimpleCPUOffloadConnector] Fix remaining global→block conversions under PCP/DCP (#46394)
Signed-off-by: Jeff Ma <jeffjma@umich.edu>
|
2026-06-24 23:05:24 -07:00 |
|
|
|
3f5a1e1733
|
[ROCm][CI] Expand basic correctness target suites (#46573)
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
Signed-off-by: Matthew Wong <Matthew.Wong2@amd.com>
Co-authored-by: Matthew Wong <Matthew.Wong2@amd.com>
Co-authored-by: Matt <156021403+mawong-amd@users.noreply.github.com>
|
2026-06-25 12:18:57 +08:00 |
|
|
|
710ebaa189
|
[ROCm][Bugfix] Fix chunk alignment when using context parallelism with TRITON_MLA (#46114)
Signed-off-by: Micah Williamson <micah.williamson@amd.com>
Co-authored-by: Andreas Karatzas <akaratza@amd.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
2026-06-25 00:07:28 -04:00 |
|
|
|
1aad125815
|
[CPU] Enable chunked prefill and prefix caching for qwen3.5 (#46202)
Signed-off-by: Li, Tianmu <tianmu.li@intel.com>
Co-authored-by: Claude Sonnet 4.6 (1M context) <noreply@anthropic.com>
Co-authored-by: Li, Jiang <jiang1.li@intel.com>
|
2026-06-25 03:49:21 +00:00 |
|
|
|
dc55936f64
|
[AMD][CI] Fix Pipeline + Context Parallelism test group (#46650)
Signed-off-by: aarushjain29 <Aarushi.Jain2@amd.com>
Co-authored-by: Andreas Karatzas <akaratza@amd.com>
|
2026-06-24 22:23:42 -05:00 |
|
|
|
9e88e969c0
|
[Perf][KVConnector][Mooncake] Parallelize KV load with a receive-thread pool (#45971)
Signed-off-by: Yifan Qiao <yifanqiao@inferact.ai>
Co-authored-by: Claude <noreply@anthropic.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
2026-06-24 18:25:12 -07:00 |
|
|
Maxwill LinandGitHub
|
cd347298e8
|
[Frontend] Port seed_oss to the streaming parser engine as a Qwen3 subclass (#46314)
Signed-off-by: EazyReal <8047065+EazyReal@users.noreply.github.com>
|
2026-06-24 20:08:42 -04:00 |
|
|
Yifan QiaoandGitHub
|
b69816043a
|
[Bugfix][MooncakeStore] track resumed requests via scheduler's resumed_req_ids (#46595)
Signed-off-by: Yifan Qiao <yifanqiao@inferact.ai>
|
2026-06-24 23:50:56 +00:00 |
|
|
Kaihang JiangandGitHub
|
fc7fc421e9
|
[Kernel][MoE] Allow FlashInfer MXINT4 MoE for gated SiLU (#46518)
Signed-off-by: Kaihang Jiang <kaihangj@nvidia.com>
|
2026-06-24 18:32:50 -05:00 |
|
|
cyqandGitHub
|
e06a83445c
|
[Bugfix] Normalize slashes in Helion GPU names (#46101)
Signed-off-by: cyq <15000851237@163.com>
|
2026-06-24 18:22:49 -05:00 |
|
|
ChaunceyandGitHub
|
84c2f9f0fb
|
[Frontend] Fix Kimi K2 tool call IDs for required tool choice (#46344)
Signed-off-by: chaunceyjiang <chaunceyjiang@gmail.com>
|
2026-06-24 19:59:40 +00:00 |
|
|
|
49f2104c53
|
[Feature] Support DCP with FP8 KV cache in MLA decode path (#44044)
Signed-off-by: shivampr <shivampr.dev@gmail.com>
Signed-off-by: Shivam <shivamprasad91@gmail.com>
Co-authored-by: Matthew Bonanni <mbonanni@redhat.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
2026-06-24 19:28:17 +00:00 |
|
|
|
3c43237233
|
[Bugfix][Model Runner V2][Spec Decode] Fix int32 offset overflow in sampler kernels (#46560)
Signed-off-by: xiaojun.wei <jessiewei747@gmail.com>
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
Co-authored-by: Robert Shaw <114415538+robertgshaw2-redhat@users.noreply.github.com>
|
2026-06-24 11:00:57 -07:00 |
|
|
Lucas WilkinsonandGitHub
|
e7df232288
|
[KV Offload] Gate packed HMA KV cache on cross-layer config (#46252)
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
|
2026-06-24 11:55:30 -04:00 |
|
|
|
b3a688cb9e
|
[ROCm] Fix OOB During Model Warmup With ROCM_ATTN and MRV2 (#46548)
Signed-off-by: Micah Williamson <micah.williamson@amd.com>
Signed-off-by: Matthew Wong <Matthew.Wong2@amd.com>
Co-authored-by: Matthew Wong <Matthew.Wong2@amd.com>
|
2026-06-24 10:53:21 -05:00 |
|
|
|
bb61177e49
|
[KV Offloading] Replace bool|None lookup return with LookupResult enum (#46363)
Signed-off-by: Ronen Schaffer <ronen.schaffer@ibm.com>
Co-authored-by: Or Ozeri <oro@il.ibm.com>
|
2026-06-24 18:06:08 +03:00 |
|
|
|
7f99e80c3b
|
[Perf][ThinkingBudget] reduce search space for thinking tokens (#46425)
Signed-off-by: walterbm <walter.beller.morales@gmail.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
2026-06-24 23:02:25 +08:00 |
|
|
|
2801b11156
|
[Test] Pin block_size in auto-fit max_model_len test (#45914)
Signed-off-by: Ma, Liangliang <liangliang.ma@intel.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
2026-06-24 22:56:21 +08:00 |
|
|
|
61ee183d28
|
[ROCm] Fix AITER FP8 quantization schema tests (#46414)
Signed-off-by: Djordje Ramic <djoramic@amd.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
2026-06-24 22:29:19 +08:00 |
|
|
Fadi ArafehandGitHub
|
061043eaca
|
[CPU][Perf] Accelerate unquantized MoE for AArch64 (#46353)
Signed-off-by: Fadi Arafeh <fadi.arafeh@arm.com>
|
2026-06-24 14:14:35 +00:00 |
|
|
|
cf9fd6457e
|
Fix KV offload request-finished lifecycle contract (#46284)
Signed-off-by: test test <2260891073@qq.com>
Signed-off-by: Rui Yin <2260891073@qq.com>
Co-authored-by: Or Ozeri <oro@il.ibm.com>
|
2026-06-24 15:42:40 +03:00 |
|
|
Martin HickeyandGitHub
|
f237e16b41
|
[KV Offload] Replace OffloadingHandler with OffloadingWorker (#45053)
Signed-off-by: Martin Hickey <martin.hickey@ie.ibm.com>
|
2026-06-24 14:44:24 +03:00 |
|
|
|
70749fdcca
|
[Feature] Triton INT4 per-token-head KV cache quantization (#40835)
Signed-off-by: JartX <sagformas@epdcenter.es>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
2026-06-24 10:21:25 +00:00 |
|
|
|
d20dbf921b
|
[Mooncake] Only check and store new KV cache range (#46412)
Signed-off-by: wzhao18 <wzhao18.sz@gmail.com>
Signed-off-by: Yifan Qiao <yifanqiao@inferact.ai>
Co-authored-by: Yifan Qiao <yifanqiao@inferact.ai>
|
2026-06-24 03:10:50 -07:00 |
|
|
|
4cd1a84c88
|
[Model] Remove BaiChuanForCausalLM and BaichuanForCausalLM (#46362)
Signed-off-by: Xianbao QIAN <xianbao.qian@gmail.com>
Co-authored-by: Claude <noreply@anthropic.com>
|
2026-06-24 16:13:57 +08:00 |
|
|
Andreas KaratzasandGitHub
|
549c7074cd
|
[ROCm][CI] Skip the MoE Marlin tile-padding helper assertion (#46580)
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
|
2026-06-24 07:31:33 +00:00 |
|
|
|
489abadfb8
|
feat: support to OpenMOSS-Team (#44124)
Signed-off-by: nagisa-kun <1434936049@qq.com>
Signed-off-by: nagisa19 <1434936049@qq.com>
Signed-off-by: nagisa <1434936049@qq.com>
Co-authored-by: OpenAI Codex <codex@openai.com>
Co-authored-by: Roger Wang <hey@rogerw.io>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
2026-06-24 00:08:13 -07:00 |
|
|
Benjamin ChislettandGitHub
|
4c5bc41ba6
|
[Bugfix][Spec Decode] Fix probabilistic sampling for parallel drafting (#45956)
Signed-off-by: Benjamin Chislett <bchislett@nvidia.com>
|
2026-06-24 05:36:23 +00:00 |
|
|
Wei ZhaoandGitHub
|
05a0caba91
|
[Mooncake] Optimize lookup pool key string construction (#46188)
Signed-off-by: wzhao18 <wzhao18.sz@gmail.com>
|
2026-06-24 11:51:53 +08:00 |
|
|
Nick HillandGitHub
|
7ee4d22009
|
[Spec Decode] Reject placeholder (-1) draft tokens in rejection sampler (#46533)
Signed-off-by: Nick Hill <nickhill123@gmail.com>
|
2026-06-24 03:32:32 +00:00 |
|
|
|
6af0559ddb
|
[Core][DP] Throttle prefills based on local prefill work (#46532)
Signed-off-by: Nick Hill <nickhill123@gmail.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
2026-06-24 02:27:12 +00:00 |
|
|
Maxwill LinandGitHub
|
e48f2aa4ca
|
[Bugfix][Frontend] Emit a content block for empty Anthropic completions (#46525)
Signed-off-by: EazyReal <8047065+EazyReal@users.noreply.github.com>
|
2026-06-24 00:04:26 +00:00 |
|
|
Roberto L. CastroandGitHub
|
d86c66c981
|
[Feat] Add runtime monitor for post-warmup CuTeDSL compilation (#46167)
|
2026-06-23 23:33:17 +00:00 |
|
|
Roberto L. CastroandGitHub
|
855cd4d787
|
[Perf][DSv4/DSv3.2] Add cluster-cooperative topK kernel for low-latency scenarios (#43008)
Signed-off-by: LopezCastroRoberto <rocastro@redhat.com>
|
2026-06-23 16:11:00 -07:00 |
|
|
|
0a3e2dbc09
|
[Optimization] Skip DP padding tokens in MoE (#46428)
Signed-off-by: Woosuk Kwon <woosuk@inferact.ai>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
2026-06-23 14:54:46 -07:00 |
|
|
|
84f13374b3
|
[CI] Fix test_auto_gptq on ROCm CI (#46164)
Signed-off-by: Felix Marty <Felix.Marty@amd.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
2026-06-23 16:38:06 -05:00 |
|
|
Micah WilliamsonandGitHub
|
b28103e1ca
|
[ROCm][CI] Shard LM Eval Qwen3-5 Models (B200-MI355) in AMD CI (#46520)
Signed-off-by: Micah Williamson <micah.williamson@amd.com>
|
2026-06-23 16:32:05 -05:00 |
|
|
Wentao YeandGitHub
|
abc33134fa
|
[CI Test] Mark batch invariance test flaky (#46530)
Signed-off-by: yewentao256 <zhyanwentao@126.com>
Signed-off-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com>
|
2026-06-23 21:01:34 +00:00 |
|
|
|
6617db1bfb
|
[Bugfix][Frontend] Emit non-ASCII tool-call arguments without \uXXXX escapes (#46308)
Signed-off-by: EazyReal <8047065+EazyReal@users.noreply.github.com>
Co-authored-by: EazyReal <8047065+EazyReal@users.noreply.github.com>
|
2026-06-23 20:43:11 +00:00 |
|
|
|
899d72a58c
|
[Bugfix][ToolParser] Handle braces in required tool streaming strings (#45389)
Signed-off-by: Ting Sun <suntcrick@gmail.com>
Co-authored-by: Flora Feng <4florafeng@gmail.com>
|
2026-06-23 20:29:34 +00:00 |
|
|
Yan MaandGitHub
|
acce57d8dd
|
Deprecate old FP8 online MoE quantization class (#44514)
Signed-off-by: Yan Ma <yan.ma@intel.com>
|
2026-06-23 11:53:38 -07:00 |
|
|
|
37a682d392
|
[Kernel] Extend Marlin thread-tile padding to MoE (WNA16 + FP8/MXFP8) (#45703)
Signed-off-by: mgoin <mgoin64@gmail.com>
Co-authored-by: Claude <noreply@anthropic.com>
|
2026-06-23 11:45:10 -07:00 |
|
|
Rui YinandGitHub
|
d8e422ccda
|
[Bugfix] Parse MiniMax M3 streaming reasoning by text markers (#45718)
Signed-off-by: test test <2260891073@qq.com>
|
2026-06-23 14:43:58 -04:00 |
|
|
fxmarty-amdandGitHub
|
e368415daa
|
[AMD][OCP MX][CI] Fix tests to not dispatch on UNFUSED_TRITON backend on MI300, improve w_mxfp4_a_fp8 emulation support (#46142)
Signed-off-by: Felix Marty <Felix.Marty@amd.com>
|
2026-06-23 14:25:27 -04:00 |
|