Skip to content

Pull requests: jd-opensource/xllm

New pull request New
80 Open 1,268 Closed
80 Open 1,268 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

feat: support dumping xllm server flags to json file.
#1518 opened May 22, 2026 by XuZhang99 Collaborator Loading…
2
feat:remove unused func and support deepseek_v4_mtp graph on npu.
#1517 opened May 22, 2026 by panxua Contributor Loading…
7
feat: expose cached token usage in responses.
#1514 opened May 21, 2026 by zhang-minchao Collaborator Loading…
2
bugfix: fix precision issue of TileLang operator chunk_gated_delta_ru…
#1510 opened May 21, 2026 by fengz72 Loading…
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 Loading…
7
feat: add rate limit, monitor, multiple images and input validation for dit.
#1483 opened May 19, 2026 by xiao-yu-chen Collaborator Loading…
3
feat: support customized multimodal preprocess configs.
#1481 opened May 19, 2026 by xanecdotex Collaborator • Draft
4
refactor: remove negative condition when choosing decode or prefill
#1475 opened May 18, 2026 by rauletorresc Contributor Loading…
feat: parallelize multimodal decode in request transfer.
#1474 opened May 18, 2026 by wly-115 Collaborator Loading…
6
refactor: split forward inputs from model input params [3 / 3].
#1469 opened May 18, 2026 by RobbieLeung Collaborator Loading…
15
bugfix: ensure tensor contiguous layout before protobuf serialization.
#1468 opened May 18, 2026 by a120092009 Collaborator Loading…
4
fused_sigmoid_gating_tilelang tilelang adapt in qwen3.x
#1465 opened May 15, 2026 by BikingNow Loading…
10
feat: Support Flux2 in other common components
#1463 opened May 15, 2026 by wang-shuibin Loading…
7
bugfix: reduce acl graph memory overhead.
#1457 opened May 15, 2026 by RobbieLeung Collaborator Loading…
2
docs: exporting a draft model from a quantized model.
#1455 opened May 14, 2026 by rauletorresc Contributor Loading…
8
【WIP】feat: onerec xattn npu multistream.
#1453 opened May 14, 2026 by DragonFive Collaborator • Draft
18
feat: support text_encoder for flux2
#1452 opened May 14, 2026 by wang-shuibin Loading…
13
feat: use FIA for qwen3.5 prefill attention on npu.
#1448 opened May 14, 2026 by Sinle4Cat Loading…
4
feat: support vae for wan2.2
#1447 opened May 14, 2026 by ethan686 Contributor Loading…
13
feat: support the wan22's dit and tp parallel.
#1445 opened May 14, 2026 by ethan686 Contributor Loading…
9
feat: support the /v1/video/generation for wan2.2.
#1444 opened May 13, 2026 by ethan686 Contributor Loading…
14
ProTip! Mix and match filters to narrow down what you’re looking for.