|
54f548e9e5
|
[Bugfix] Restore moe_forward output shape invariant on TRTLLM MXFP4 path (#41646)
Signed-off-by: Stefano Castagnetta <scastagnetta@nvidia.com>
Co-authored-by: Yongye Zhu <zyy1102000@gmail.com>
|
2026-05-07 15:26:06 -07:00 |
|
|
Kyle SayersandGitHub
|
c1819ca283
|
[Compressed Tensors] Allow configs with non-explicit ignores (#41965)
Signed-off-by: Kyle Sayers <kylesayrs@gmail.com>
|
2026-05-07 14:03:45 -07:00 |
|
|
|
969fbfb4a9
|
Laguna xs dflash support (#41880)
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
|
2026-05-07 13:31:16 -07:00 |
|
|
akii96andGitHub
|
3af561ec0a
|
[ROCm] Fix AITER AR+RMSNorm no-residual fusion (#41972)
Signed-off-by: Aakif Nawaz <aakif.nawaz@amd.com>
|
2026-05-07 13:14:58 -07:00 |
|
|
akii96andGitHub
|
c936548ce6
|
[ROCm][DeepSeek] Enable V3.2 TP4 AITER MLA (#41835)
Signed-off-by: Aakif Nawaz <aakif.nawaz@amd.com>
|
2026-05-07 15:10:57 -05:00 |
|
|
TomerBN-NvidiaandGitHub
|
8189a15914
|
[Core] Replace routing replay with device cache and async D2H pipeline (#39917)
Signed-off-by: Tomer Barnatan <tbarnatan@nvidia.com>
|
2026-05-07 11:24:56 -07:00 |
|
|
Flora FengandGitHub
|
8eb401134e
|
[Refactor] Consolidate required/named tool_choice streaming into DelegatingParser (#41876)
Signed-off-by: sfeng33 <4florafeng@gmail.com>
|
2026-05-07 09:50:59 -07:00 |
|
|
Nicolò LucchesiandGitHub
|
9d6500b89d
|
[Misc] Delay EPLB Nixl import until needed (#41805)
Signed-off-by: NickLucche <nlucches@redhat.com>
|
2026-05-07 09:43:07 -07:00 |
|
|
zhrrrandGitHub
|
7a08b34fbf
|
[Model Runner V2] support qwen35 / mamba hybrid model (#35520)
Signed-off-by: zhuhaoran <zhuhaoran.zhr@alibaba-inc.com>
|
2026-05-07 09:31:05 -07:00 |
|
|
noobHappylifeandGitHub
|
06a60d3dd0
|
Fix spec decode benchmark metrics (#41916)
Signed-off-by: noobhappylife <aratar1991@hotmail.com>
|
2026-05-07 09:23:21 -07:00 |
|
|
|
2a16ece2d3
|
tokenizer: Add fastokens support (#41741)
Signed-off-by: AlonKejzman <alonkeizman@gmail.com>
Co-authored-by: Roger Wang <hey@rogerw.io>
|
2026-05-07 22:49:42 +08:00 |
|
|
Andreas KaratzasandGitHub
|
003159d98b
|
[ROCm][CI] Avoid duplicate ROCm AITER norm-quant patterns (#41534)
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
|
2026-05-07 06:33:30 -07:00 |
|
|
|
2a84da3b17
|
[XPU] Implement out-of-place all-reduce functionality (#41808)
Signed-off-by: Chaojun,Zhang <chaojun.zhang@intel.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
2026-05-07 05:58:05 -07:00 |
|
|
Chaojun ZhangandGitHub
|
805e9f7b77
|
[XPU] Fix lora bugs & enable UTs under tests/lora (#38206)
Signed-off-by: chaojun-zhang <chaojun.zhang@intel.com>
|
2026-05-07 05:58:00 -07:00 |
|
|
s-yanevandGitHub
|
75f0d516c4
|
[Bugfix] Fix GLM4-MoE weight loading for NVFP4 quantized checkpoints (#41755)
Signed-off-by: Stoyan Yanev <stoyan.yanev@cleverpine.com>
|
2026-05-07 05:55:52 -07:00 |
|
|
|
f650ace6de
|
[MM][Gemma4] Use video profiling hints in encoder budget (#41837)
Signed-off-by: lesj0610 <lesj0610@users.noreply.github.com>
Co-authored-by: lesj0610 <lesj0610@users.noreply.github.com>
|
2026-05-07 05:46:04 -07:00 |
|
|
Li, JiangandGitHub
|
b3945cc316
|
[CPU] Bump up to the latest CPU kernels (#41924)
Signed-off-by: jiang1.li <jiang1.li@intel.com>
|
2026-05-07 05:45:59 -07:00 |
|
|
|
ffee741626
|
[Model] Use AutoWeightsLoader for AXK1 (#41901)
Signed-off-by: liwenyi <lwy.lwy@163.com>
Co-authored-by: Claude <noreply@anthropic.com>
|
2026-05-07 05:40:29 -07:00 |
|
|
Jee Jee LiandGitHub
|
9c0812ffd0
|
[Bugfix] Fix FusedMoEWithLoRA has no attribute runner (#41889)
Signed-off-by: Jee Jee Li <jeejeelee@inferact.ai>
|
2026-05-07 04:53:14 -07:00 |
|
|
Fadi ArafehandGitHub
|
b20731d0ae
|
[CI][Arm] skip e2e model tests if HF_TOKEN is not set (#41919)
Signed-off-by: Fadi Arafeh <fadi.arafeh@arm.com>
|
2026-05-07 11:31:50 +00:00 |
|
|
|
d4b0048404
|
Eliminate redundant MoE buffer copies in AITER fused experts (without dependency on AITER changes) (#41713)
Signed-off-by: Mehdi Ghanimifard <mehdi.ghanimifard@amd.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
2026-05-07 03:46:40 -07:00 |
|
|
|
6e6d182d18
|
[Bugfix] Fix OOM in tensorizer LoRA deserialization (#41845)
Signed-off-by: Or Ozeri <oro@il.ibm.com>
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
|
2026-05-07 02:17:47 -07:00 |
|
|
tejandGitHub
|
8a4888be21
|
[ROCm] Profiler api support for ROCm MORI toy proxy server in PD Disaggregation (#40264)
Signed-off-by: Tej Kiran <kiran.tej@amd.com>
|
2026-05-07 16:58:38 +08:00 |
|
|
Yuwen ZhouandGitHub
|
713b28bd0b
|
[CPU] Add FP8 W8A16 MoE support (#41314)
Signed-off-by: yuwenzho <yuwen.zhou@intel.com>
|
2026-05-06 23:17:07 -07:00 |
|
|
|
51f22dcfd0
|
[Feat][CPU] Enable Gated DeltaNet Attention (Qwen 3.5 / 3.6) (#41025)
Signed-off-by: Fadi Arafeh <fadi.arafeh@arm.com>
Co-authored-by: Vadim Gimpelson <156319763+vadiklyutiy@users.noreply.github.com>
|
2026-05-07 12:57:09 +08:00 |
|
|
|
20cac26b19
|
[ROCm] Enable SimpleCPUOffloadConnector on ROCm (#40549)
Signed-off-by: Hongxia Yang <hongxia.yang@amd.com>
Co-authored-by: TJian <tunjian.tan@embeddedllm.com>
|
2026-05-06 20:52:02 -07:00 |
|
|
Russell BryantandGitHub
|
5a0a8fc1ea
|
[Docs] add cache directory security guidance (#38920)
Signed-off-by: Russell Bryant <rbryant@redhat.com>
|
2026-05-06 16:54:29 -07:00 |
|
|
Micah WilliamsonandGitHub
|
7a576e2c72
|
[ROCm][CI] Remove TORCH_NCCL_BLOCKING_WAIT=1 After Bugfix In ROCm 7.2 (#41840)
Signed-off-by: Micah Williamson <micah.williamson@amd.com>
|
2026-05-06 16:37:11 -07:00 |
|
|
Yongye ZhuandGitHub
|
80d5e7d103
|
[Bugfix] Fix condition to clear persistent topk so that it can be captured regardless (#41665)
Signed-off-by: Yongye Zhu <zyy1102000@gmail.com>
|
2026-05-06 16:17:48 -07:00 |
|
|
|
95582868ef
|
[Bugfix] DeepSeekV32/v4: respect string='true|false' attribute andunwrap arguments/input wrapper (#41801)
Signed-off-by: chaunceyjiang <chaunceyjiang@gmail.com>
Co-authored-by: QwertyJack <7554089+QwertyJack@users.noreply.github.com>
|
2026-05-06 21:48:01 +00:00 |
|
|
|
50acdc5b5c
|
Fix Qwen3 streaming content routing (#40820)
Signed-off-by: xy3 <120182408@qq.com>
Signed-off-by: sfeng33 <4florafeng@gmail.com>
Co-authored-by: sfeng33 <4florafeng@gmail.com>
|
2026-05-06 17:22:01 -04:00 |
|
|
JackyLiuandGitHub
|
deb737e323
|
[Doc] Add ModernBertForSequenceClassification to scoring.md cross-en… (#41832)
Signed-off-by: JLiu4Coding <lzwgre@126.com>
|
2026-05-06 14:17:56 -07:00 |
|
|
Flora FengandGitHub
|
f3f8efa73a
|
[CI] Enable gemma4 parser test on CI (#41857)
Signed-off-by: sfeng33 <4florafeng@gmail.com>
|
2026-05-06 20:25:34 +00:00 |
|
|
Johnny YangandGitHub
|
ca3e62d336
|
Upgrade tpu-inference to v0.19.0 (#41844)
Signed-off-by: Johnny Yang <johnnyyang@google.com>
|
2026-05-06 11:41:37 -07:00 |
|
|
Benjamin ChislettandGitHub
|
38e16678ba
|
[Bugfix] Align block table for TRTLLM MLA edge-case (#39324)
Signed-off-by: Benjamin Chislett <bchislett@nvidia.com>
|
2026-05-06 11:17:02 -07:00 |
|
|
|
27702f6d08
|
[Bugfix] Fix token loss in PP mode which causes degraded accuracy (#41133)
Signed-off-by: Jing Wang <jingwang96@qq.com>
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
Co-authored-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
2026-05-06 14:07:32 -04:00 |
|
|
Divakar VermaandGitHub
|
22a3cbe152
|
[ROCm] aiter_unified_attn fp8 q scale refactor (#38296)
Signed-off-by: Divakar Verma <divakar.verma@amd.com>
|
2026-05-06 16:11:36 +00:00 |
|
|
Viktor PusandGitHub
|
d5b31c954d
|
[Bugfix] Account for truncate_prompt_tokens when computing max_tokens (#41800)
Signed-off-by: Viktor Pus <viktorpus@tenstorrent.com>
|
2026-05-06 16:10:17 +00:00 |
|
|
David ZhengandGitHub
|
ee38750a75
|
[Bugfix] Fix spawn_new_process_for_each_test silently swallowing test failures (#41423)
Signed-off-by: dqzhengAP <dqzheng1996@gmail.com>
|
2026-05-06 11:17:15 -04:00 |
|
|
|
27e0057aed
|
[Spec Decode] Add Gemma4 MTP speculative decoding support (#41745)
Signed-off-by: Luciano Martins <lucianommartins@users.noreply.github.com>
Co-authored-by: Luciano Martins <lucianommartins@users.noreply.github.com>
|
2026-05-06 22:39:29 +08:00 |
|
|
Ronen SchafferandGitHub
|
f39bcf1e30
|
[KV Offload] Return None from lookup() for in-flight blocks (#41795)
Signed-off-by: Ronen Schaffer <ronen.schaffer@ibm.com>
|
2026-05-06 17:31:21 +03:00 |
|
|
|
6467213a9f
|
fix(openai): tolerate empty content in forced tool choice (#40148)
Signed-off-by: QwertyJack <7554089+QwertyJack@users.noreply.github.com>
Signed-off-by: chaunceyjiang <chaunceyjiang@gmail.com>
Co-authored-by: QwertyJack <7554089+QwertyJack@users.noreply.github.com>
Co-authored-by: chaunceyjiang <chaunceyjiang@gmail.com>
|
2026-05-06 07:16:03 -07:00 |
|
|
|
df8e63f4ed
|
nixl refactor: new transfer design (#40731)
Signed-off-by: ZhanqiuHu <zhu@redhat.com>
Signed-off-by: NickLucche <nlucches@redhat.com>
Co-authored-by: NickLucche <nlucches@redhat.com>
|
2026-05-06 06:16:25 -07:00 |
|
|
|
242afc6bf4
|
[MM][Gemma4] Respect max_soft_tokens in encoder budget (#41799)
Signed-off-by: lesj0610 <lesj0610@users.noreply.github.com>
Co-authored-by: lesj0610 <lesj0610@users.noreply.github.com>
Co-authored-by: gemini-code-assist <gemini-code-assist@google.com>
|
2026-05-06 05:54:42 -07:00 |
|
|
lyd1992andGitHub
|
5d0fd87038
|
[CPU][RISC-V] Auto-bind OMP threads and harden nobind path (#40569)
Signed-off-by: liuyudong <liuyudong@iscas.ac.cn>
|
2026-05-06 11:38:08 +00:00 |
|
|
Harry MellorandGitHub
|
d8deb5b7ad
|
Fix some legacy checkpoints with deprecated rope_type values (#41734)
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
|
2026-05-06 11:13:12 +00:00 |
|
|
|
2e777d21a8
|
[Bugfix][Rocm]Aiter MoE re-uses existing tensor addresses after weight update. (#40390)
Signed-off-by: Yuankai Chen <yuankach@amd.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
|
2026-05-06 10:32:26 +00:00 |
|
|
Nicolò LucchesiandGitHub
|
e43a791284
|
[Bugfix][CI] Fix Disaggregated test area path (#41794)
Signed-off-by: NickLucche <nlucches@redhat.com>
|
2026-05-06 17:41:24 +08:00 |
|
|
|
66d1cc0c77
|
fix(rocm): remove workaround causing invalid argument on Qwen3.5 with TP=2 (#40686)
Co-authored-by: Test User <test@example.com>
Co-authored-by: TJian <tunjian.tan@embeddedllm.com>
|
2026-05-06 01:38:32 -07:00 |
|
|
|
1c58876618
|
[XPU] Disable CUDA graph memory estimate on XPU platform (#41344)
Signed-off-by: chaojun-zhang <chaojun.zhang@intel.com>
Co-authored-by: Kunshang Ji <kunshang.ji@intel.com>
|
2026-05-06 16:38:18 +08:00 |
|