Skip to content

Pull requests: jd-opensource/xllm

New pull request New
28 Open 478 Closed
28 Open 478 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

bugfix: resolve test compile failed.
#603 opened Dec 25, 2025 by Dragonliu2018 Loading…
bugfix: handle missing global git config when building third-party xllm ops.
#602 opened Dec 25, 2025 by LMX-xin Loading…
refactor: refine layers and models for cuda device.
#597 opened Dec 25, 2025 by XuZhang99 Loading…
3
feat: implement prefix cache for decoder.
#596 opened Dec 24, 2025 by Kang-Meng Loading…
feat: support FLUX.1-Redux-dev model on npu device.
#592 opened Dec 24, 2025 by z-jun03 Loading…
6
feat: introduce USE_NPU_TORCH flag for debugging and enhance NPU support for Qwen3-Dense[4/N].
#590 opened Dec 23, 2025 by yingxudeng Loading…
11
feat: add xAttention support for Qwen3 generative recommendation.
#586 opened Dec 23, 2025 by LMX-xin Loading…
15
refactor: update causal LM implementations to inherit from LlmForCausalLMImplBase[3/N].
#583 opened Dec 22, 2025 by yingxudeng Loading…
4
bugfix: fix the missing index shape in the allocat kv cache transfer.
#574 opened Dec 19, 2025 by Clement-Wang26 Loading…
1
bugfix: fix several bugs in the read/write swap blocks.
#573 opened Dec 19, 2025 by Clement-Wang26 Loading…
1
feat: add wrapper for torch_npu layers[2/N].
#572 opened Dec 19, 2025 by yingxudeng Loading…
1
feat: add onerec worker impl for rec framework[5/8].
#567 opened Dec 18, 2025 by DragonFive Loading…
7 of 10 tasks
6
feat: support dp+ep moe and all2all computation.
#566 opened Dec 18, 2025 by a120092009 Loading…
13
refactor: rename layer and model interfaces for torch_npu preparation[1/N].
#563 opened Dec 18, 2025 by yingxudeng Loading…
5
feat: add mooncake kv cache transfer
#558 opened Dec 17, 2025 by jinke446 Loading…
16
feat: add multi-priority request scheduler slidebatching.
#554 opened Dec 16, 2025 by weizhehuang0827 Loading…
27
bugfix: support disagg PD for MTP.
#551 opened Dec 16, 2025 by RobbieLeung Loading…
1
[WIP]: feat: concurrent multi stream executor for rec_model.
#548 opened Dec 15, 2025 by zhang-minchao Loading…
9
feat: initialize flashinfer planinfo at layer-0 forward stage.
#534 opened Dec 12, 2025 by yq33victor Loading…
feat: add a new manual management weights loader style for deepseek.
#531 opened Dec 12, 2025 by Clement-Wang26 Loading…
12
feat: support custom shared memory size.
#528 opened Dec 12, 2025 by Clement-Wang26 Loading…
9
feat: support graph executor on mlu device.
#526 opened Dec 12, 2025 by a120092009 Loading…
22
feat: add mm embed worker and service.
#518 opened Dec 11, 2025 by dongxianzhe Loading…
6
refactor: remove empty_kv_cache and global_empty_kv_cache.
#514 opened Dec 10, 2025 by RobbieLeung Loading…
1
bugfix: fix the issue of ineffective input embedding transmission.
#490 opened Dec 5, 2025 by magicheng0816 Loading…
7
ProTip! What’s not been updated in a month: updated:<2025-11-25.