Skip to content

Pull requests: jd-opensource/xllm

New pull request New
85 Open 1,310 Closed
85 Open 1,310 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

Modify XLLM_OPS dependency: xllm -> custom_xllm_math
#1568 opened May 26, 2026 by ware2009 Loading…
3 of 11 tasks
2
bugfix: serialize qwen3 next attention weight transforms
#1567 opened May 26, 2026 by pjgao Contributor Loading…
refactor: add pool name when init thread pool.
#1565 opened May 26, 2026 by XuZhang99 Collaborator Loading…
3 of 17 tasks
7
feat: add rec qwen num_return_sequences in gpu and npu.
#1563 opened May 26, 2026 by DragonFive Collaborator Loading…
10 of 17 tasks
8
perf: reduce aclgraph copy operations.
#1562 opened May 26, 2026 by JC-ut0 Contributor Loading…
17 tasks
5
feat: qwen3.5 support chunked prefill.
#1551 opened May 25, 2026 by maojunx99 Contributor Loading…
5 of 13 tasks
5
bugfix: add qwen3.5 chat stop token.
#1548 opened May 25, 2026 by yingxudeng Collaborator Loading…
9 of 17 tasks
5
feat: support qwen3.5 linear-state prefix cache.
#1546 opened May 25, 2026 by yingxudeng Collaborator Loading…
17 tasks
4
feat: parallelize manual-loader decoder weight merge.
#1542 opened May 25, 2026 by Clement-Wang26 Collaborator Loading…
6
[WIP]perf: overlap mtp draft extend preparation
#1541 opened May 25, 2026 by pjgao Contributor Loading…
6
feat: support Cola-DLM on cuda device.
#1539 opened May 24, 2026 by Dragonliu2018 Contributor • Draft
9
[WIP] perf(npu): eliminate redundant Transpose in Qwen3.5 MTP spec verify conv path
#1536 opened May 23, 2026 by pjgao Contributor Loading…
7
feat: update mlu container to 26.04.
#1535 opened May 23, 2026 by phantomlei3 Collaborator Loading…
6
feat: support interlayer add norm and SplitRmsnormRope operation for qwen3.
#1531 opened May 22, 2026 by shan-chen-feng Collaborator Loading…
5
refactor: refact multimodal processor.
#1530 opened May 22, 2026 by wly-115 Collaborator Loading…
4
feat: support MiMo-7B-Base on cuda device.
#1523 opened May 22, 2026 by Dragonliu2018 Contributor Loading…
20
feat: add dcu backend support.
#1522 opened May 22, 2026 by WenQ7 Loading…
24
feat: expose cached token usage in responses.
#1514 opened May 21, 2026 by zhang-minchao Collaborator Loading…
3
refactor: remove xattention one-stage decode path.
#1504 opened May 21, 2026 by LMX-xin Collaborator • Draft
2
feat: enable REC XAttention for Qwen3 MoE on cuda device.
#1500 opened May 20, 2026 by LMX-xin Collaborator Loading…
1
feat: support vae parallel for qwen-image-edit-plus.
#1499 opened May 20, 2026 by shan-chen-feng Collaborator Loading…
13
feat: add TileLang chunk_gated_delta_rule_fwd_h kernel.
#1498 opened May 20, 2026 by fengz72 Loading…
5
bugfix: use max_concurrent_requests for single block and linear state allocation.
#1496 opened May 20, 2026 by pjgao Contributor Loading…
10
feat: support customized multimodal preprocess configs.
#1481 opened May 19, 2026 by xanecdotex Collaborator Loading…
4
refactor: remove negative condition when choosing decode or prefill
#1475 opened May 18, 2026 by rauletorresc Contributor Loading…
ProTip! Mix and match filters to narrow down what you’re looking for.