Skip to content

Pull requests: xLLM-AI/xllm

New pull request New
112 Open 1,779 Closed
112 Open 1,779 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

refactor: remove redudant USE_MUSA/USE_CUDA flags in CMakefile for musa kernels
#2077 opened Jul 29, 2026 by fay85 Collaborator Loading…
7 of 17 tasks
WIP: support deepseek v3.2 used Pytorch model
#2076 opened Jul 29, 2026 by sunbaosong Collaborator • Draft
17 tasks
feat: add Ascend950 TileLang and causal convolution support.
#2073 opened Jul 29, 2026 by wuyifan2017 Loading…
7 of 17 tasks
bugfix: fix VAE_IMAGE_SIZE calc logic.
#2069 opened Jul 29, 2026 by xiao-yu-chen Collaborator Loading…
6 of 17 tasks
build:optimize native and tilelang incremental builds.
#2068 opened Jul 29, 2026 by jarvis666666 Loading…
16 tasks
refactor: replace wan2.2 tp with linear.cpp.
#2067 opened Jul 29, 2026 by ethan686 Collaborator Loading…
feature: deepseekv4 context parallel with DSA
#2066 opened Jul 29, 2026 by LMxyzptlk Contributor Loading…
bugfix: prevent incompatible npu graph replays.
#2065 opened Jul 28, 2026 by shifengmin Collaborator Loading…
7 of 17 tasks
feat: add multimodal processor cache.
#2061 opened Jul 28, 2026 by wly-115 Collaborator • Draft
8 of 17 tasks
feat: enable NPU aclgraph backend for Python model executor.
#2053 opened Jul 28, 2026 by maojunx99 Collaborator Loading…
1 of 7 tasks
27
refactor: extract VaeParallelMixin, remove ctx pass-through in VAE.
#2052 opened Jul 28, 2026 by zhangjieshao98 Contributor Loading…
3
feat(lora): prefix cache adapter isolation (PR 3/3)
#2047 opened Jul 27, 2026 by cchh05 Collaborator Loading…
3 of 5 tasks
refactor: add runtime primitives for EPLB.
#2045 opened Jul 27, 2026 by DongheJin Collaborator Loading…
17 tasks
bugfix: keep SHM tensor views on owned buffers
#2043 opened Jul 27, 2026 by pjgao Collaborator • Draft
1
bugfix: fix multimodal data races in parallel batch building.
#2039 opened Jul 27, 2026 by wly-115 Collaborator Loading…
5 of 17 tasks
docs: update Flux2-dev quick start guide for Ascend A3.
#2032 opened Jul 25, 2026 by wang-shuibin Collaborator Loading…
9 of 17 tasks
feat: support text_encoder for flux2 on device npu
#2031 opened Jul 24, 2026 by wang-shuibin Collaborator Loading…
9 of 17 tasks
1
feat: support decode context parallel.
#2021 opened Jul 23, 2026 by phantomlei3 Collaborator • Draft
17 tasks
feat: add distill mode support for Wan2.2 I2V pipeline.
#2020 opened Jul 23, 2026 by zhangjieshao98 Contributor Loading…
1
feat: support joy-image-edit-plus on NPU device & refact sequence parallel Mixin.
#2018 opened Jul 23, 2026 by shan-chen-feng Collaborator Loading…
17 tasks
refactor: eliminate DisaggPDChunkedPrefillScheduler.
#2017 opened Jul 23, 2026 by weizhehuang0827 Collaborator Loading…
5 tasks done
feat(lora): request path adapter_id propagation + chat routing (2/2)
#2015 opened Jul 23, 2026 by cchh05 Collaborator Loading…
3
feat(lora): multi-tenant LoRA framework + attention/MLP wire-up (1/2)
#2014 opened Jul 23, 2026 by cchh05 Collaborator Loading…
3
feat: add mlu host kv cache support.
#2012 opened Jul 23, 2026 by phantomlei3 Collaborator • Draft
17 tasks
feat: add verbose request tracing and structured API error responses.
#2007 opened Jul 22, 2026 by zhang-minchao Collaborator • Draft
6 of 22 tasks
1
ProTip! Type g i on any issue or pull request to go back to the issue listing page.