Skip to content

Pull requests: jd-opensource/xllm

New pull request New
62 Open 960 Closed
62 Open 960 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Reviews
Filter by reviews
No reviews Review required Approved review Changes requested
Assignee
Filter by who’s assigned
Assigned to nobody Loading
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Pull requests list

support QwenImageEditPlus on npu device.
#1181 opened Apr 4, 2026 by shan-chen-feng Loading…
7
feat: support QwenImageEditPlus pipeline on npu deivce.
#1180 opened Apr 3, 2026 by xiao-yu-chen Loading…
7
refactor: change ModelArgs from value to shared_ptr.
#1179 opened Apr 3, 2026 by XuZhang99 Loading…
23
bugfix: fix undefined tensor device crash in DP empty-input path.
#1176 opened Apr 3, 2026 by yq33victor Loading…
feat: support etcd auth in etcd client via environment variables.
#1175 opened Apr 3, 2026 by JimHsiung Loading…
4
feat: support KIMI-K25 model on npu device.
#1174 opened Apr 3, 2026 by sanlio36 Loading…
9
bugfix: fix DeepSeek-3.2 failures when ACL Graph is enabled.
#1173 opened Apr 3, 2026 by DongheJin Loading…
3
bugfix: fix DeepSeek-3.2 failures when ACL Graph is enabled.
#1172 opened Apr 3, 2026 by DongheJin Loading…
4
bugfix: fix qwen3.5 gated delta net conv state indices for acl graph[5/N].
#1171 opened Apr 2, 2026 by yingxudeng • Draft
15
feat: add gemma_rms_norm and fused_qkvzba_split_reshape_cat operator.
#1170 opened Apr 2, 2026 by fems14 Loading…
7
feat: add cuda block copy kernel support.
#1169 opened Apr 2, 2026 by RobbieLeung Loading…
3
[wip] refact: dit_scheduler sinks to engine.
#1168 opened Apr 2, 2026 by panxua Loading…
4
feat: support mlu mla pd pull with mooncake transfer.
#1167 opened Apr 2, 2026 by phantomlei3 Loading…
7
feat: generate grouped cli help from gflags metadata.
#1162 opened Apr 2, 2026 by RobbieLeung Loading…
14
perf: optimize qwen3.5 hybrid linear cache flow[4/N].
#1160 opened Apr 1, 2026 by JC-ut0 Loading…
14
refactor: introduce MultimodalProcessor abstraction for VLM.
#1159 opened Apr 1, 2026 by wly-115 • Draft
10
feat: add constrain decodeing for onerec.
#1158 opened Apr 1, 2026 by DragonFive Loading…
16
refactor: prefer lambda to bind.
#1157 opened Apr 1, 2026 by Dragonliu2018 Loading…
12
feat: support video inference for Qwen3-VL on NPU device.
#1151 opened Mar 31, 2026 by xanecdotex Loading…
11
bugfix: make CP compatible with MTP.
#1150 opened Mar 31, 2026 by shifengmin Loading…
16
feat: support FIA for qwen model on npu device.
#1147 opened Mar 31, 2026 by sanlio36 Loading…
8
bugfix: rollback shared prefix blocks on allocate failure.
#1146 opened Mar 31, 2026 by RobbieLeung Loading…
4
feat: support flux model on mlu device.
#1138 opened Mar 30, 2026 by phantomlei3 Loading…
4
feat: support embedding interface for all generate VLM models.
#1136 opened Mar 30, 2026 by xanecdotex Loading…
3
perf: optimize qwen3.5 hybrid linear cache flow[4/N].
#1130 opened Mar 30, 2026 by yingxudeng • Draft
5
ProTip! Find all pull requests that aren't related to any open issues with -linked:issue.