Skip to content

Pull requests: xLLM-AI/xllm

New pull request New
119 Open 1,929 Closed
119 Open 1,929 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: add sequence parallel and cache support for Flux DiT.
#2236 opened Aug 13, 2026 by z-jun03 Collaborator Loading…
8 of 17 tasks
feat: add MUSA CICD supports.
#2235 opened Aug 13, 2026 by fay85 Collaborator Loading…
8 of 17 tasks
feat: add Python linting and formatting with ruff + codespell.
#2234 opened Aug 13, 2026 by yingxudeng Collaborator Loading…
17 tasks
fix: avoid unnecessary brpc recompilation.
#2232 opened Aug 13, 2026 by Kang-Meng Collaborator Loading…
17 tasks
feat: adaptive speculative decoding for DFlash and DSpark on NPU.
#2231 opened Aug 13, 2026 by weizhehuang0827 Collaborator Loading…
refactor: sp refactor for flux2 dit module on device npu
#2229 opened Aug 13, 2026 by wang-shuibin Collaborator Loading…
9 of 17 tasks
feat: bridge DeepSeek V4 Python caches and metadata.
#2228 opened Aug 13, 2026 by 0moyi0-2024 Loading…
1
feat: enable dit cache for wan dual transformers.
#2226 opened Aug 13, 2026 by z-jun03 Collaborator Loading…
3 of 8 tasks
feat: support the wan22 matmulall2all.
#2224 opened Aug 13, 2026 by ethan686 Collaborator Loading…
refactor: qwen_image_edit's sp use ditspmixin.
#2221 opened Aug 13, 2026 by ethan686 Collaborator Loading…
feat: support flux2 klein for xllm on device npu
#2219 opened Aug 13, 2026 by wang-shuibin Collaborator Loading…
17 tasks
feat: add asynchronous host kv cache transfers.
#2217 opened Aug 13, 2026 by phantomlei3 Collaborator Loading…
7 of 13 tasks
4
bugfix: Align empty DP shards for Qwen3.5 MTP ACL graphs.
#2214 opened Aug 13, 2026 by Enguikong Contributor • Draft
4 of 17 tasks
bugfix: clean NPU process shutdown (bypass process-static destructors).
#2209 opened Aug 12, 2026 by Enguikong Contributor Loading…
1
refactor: add dit cache mixin.
#2208 opened Aug 12, 2026 by xiao-yu-chen Collaborator • Draft
5 of 17 tasks
feat: append vit executor for qwen3 vl model
#2207 opened Aug 12, 2026 by AmpereKowk Loading…
1 of 17 tasks
feat: support kda fla_npu operator build and execute_linear integration.
#2206 opened Aug 12, 2026 by sunbaosong Collaborator Loading…
7
docs: add readme for joy-image-edit-plus.
#2203 opened Aug 12, 2026 by shan-chen-feng Collaborator Loading…
17 tasks
perf: enable double-buffer graph decode for the VLM backend.
#2202 opened Aug 12, 2026 by wly-115 Collaborator Loading…
8 of 17 tasks
perf: optimize DeepSeek V3.2 Python execution.
#2199 opened Aug 11, 2026 by yt-zeng Collaborator Loading…
1 of 7 tasks
1
perf: drop multimodal mrope handling on npu decode path.
#2196 opened Aug 11, 2026 by wly-115 Collaborator Loading…
7 of 17 tasks
fix: prefer top-level config.json for backend detection.
#2192 opened Aug 11, 2026 by weizhehuang0827 Collaborator Loading…
4 tasks
perf: adapt Qwen W8A8 quantization for FlashComm.
#2187 opened Aug 11, 2026 by Cooofish Contributor Loading…
6 of 17 tasks
9
feat(sfa): override sparse_flash_attention to PR#6 contract (3 outputs / 8 attrs, rope=None supported)
#2185 opened Aug 11, 2026 by 0moyi0-2024 Loading…
1
feat(lora): multi-tenant HTTP hot-swap API + cross-node broadcast + dense qwen3 preload
#2181 opened Aug 10, 2026 by cchh05 Collaborator Loading…
3 tasks
ProTip! Filter pull requests by the default branch with base:main.