Skip to content

Pull requests: xLLM-AI/xllm

New pull request New
94 Open 1,637 Closed
94 Open 1,637 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 Wan2.2 distill model.
#1910 opened Jul 8, 2026 by ethan686 Collaborator Loading…
1
perf: optimize qwen3.5 mtp prefill on npu.
#1907 opened Jul 8, 2026 by pjgao Collaborator Loading…
feat: add request trace dump with runtime toggle.
#1906 opened Jul 7, 2026 by shifengmin Collaborator Loading…
8 of 17 tasks
3
bugfix: update xllm_ops submodule for dynamic mega chunk gdn heads.
#1902 opened Jul 7, 2026 by Sinle4Cat Contributor Loading…
7 of 17 tasks
1
feat: implement single-process mode on npu device.
#1894 opened Jul 6, 2026 by XuZhang99 Collaborator Loading…
8 of 17 tasks
4
feat: add embedded-python model executor for qwen3 on cuda.
#1891 opened Jul 6, 2026 by zhang-minchao Collaborator Loading…
4 of 7 tasks
72
feat: Add FlashComm1 and MMRS fusion support for Qwen3.5 NPU.
#1890 opened Jul 6, 2026 by Cooofish Loading…
21
perf: route Qwen3.5 FSGDR model path to TileLang.
#1889 opened Jul 6, 2026 by ShareableXue Contributor Loading…
7 of 17 tasks
2
feat: add DFlash block-diffusion speculative decoding on npu device.
#1886 opened Jul 3, 2026 by ustcfy Collaborator Loading…
2 of 7 tasks
22
feat: add qwen image edit dcu batch support.
#1878 opened Jul 2, 2026 by WenQ7 Collaborator Loading…
8 of 17 tasks
13
feat: support adaptive speculative decoding.
#1876 opened Jul 2, 2026 by weizhehuang0827 Collaborator Loading…
7 of 17 tasks
9
Cp chunkprefill upstream 20260610 latest
#1872 opened Jul 2, 2026 by cchh05 Collaborator Loading…
17 tasks
6
feat: add RainFusion sparse attention for wan2.2.
#1867 opened Jul 1, 2026 by ethan686 Collaborator Loading…
10
feat: add ViT encoder ACL Graph capture for Qwen3-VL.
#1866 opened Jul 1, 2026 by sunbaosong Collaborator Loading…
19
docs: remove docs dir.
#1865 opened Jul 1, 2026 by XuZhang99 Collaborator Loading…
7 of 17 tasks
1
feat: support multi machine for offline inference.
#1863 opened Jul 1, 2026 by weizhehuang0827 Collaborator Loading…
9 of 12 tasks
2
Ref blockmgr4
#1861 opened Jul 1, 2026 by Kang-Meng Collaborator • Draft
17 tasks
10
feat: add prefix-cache-affinity dp rank routing.
#1860 opened Jul 1, 2026 by shifengmin Collaborator Loading…
7 of 15 tasks
6
feat: add VAE parallel for wan22 and QwenImageEdit.
#1858 opened Jul 1, 2026 by ethan686 Collaborator Loading…
15
feat: update CMake configuration for xllm_ops vendor directory and ma…
#1856 opened Jun 30, 2026 by msmilezz Collaborator Loading…
17 tasks
2
feat: enable SwiGluQuant fusion for Qwen3 MLP
#1847 opened Jun 29, 2026 by nie-linfeng Contributor Loading…
4
feat: add linear-state block manager and prefix cache (3/n).
#1846 opened Jun 29, 2026 by yingxudeng Collaborator Loading…
1 of 17 tasks
13
[WIP]feat: support qwen3.5 linear-state prefix cache.
#1839 opened Jun 27, 2026 by yingxudeng Collaborator • Draft
17 tasks
5
bugfix: synchronize MTP compute stream after draft/validate forward.
#1838 opened Jun 27, 2026 by yingxudeng Collaborator Loading…
17 tasks
4
feat: add beam search torch support to mlu.
#1835 opened Jun 27, 2026 by phantomlei3 Collaborator • Draft
17 tasks
7
ProTip! Type g i on any issue or pull request to go back to the issue listing page.