Skip to content

Pull requests: ModelTC/LightLLM

New pull request New
52 Open 1,042 Closed
52 Open 1,042 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: Qwen3.5 / Qwen3.5-MoE MTP speculative decoding
#1330 opened Jun 4, 2026 by sufubao Collaborator Loading…
4 tasks done
2
Fix NIXL PD abort handling
#1329 opened Jun 2, 2026 by WuSiYu Collaborator Loading…
3
add Flashinfer sampling backend
#1328 opened Jun 2, 2026 by blueswhen Collaborator Loading…
2
Fa4 support
#1327 opened Jun 2, 2026 by blueswhen Collaborator Loading…
10
add in-process URL pool caching
#1325 opened Jun 1, 2026 by Owleye4 Contributor Loading…
3
add log for pd nixl
#1324 opened May 29, 2026 by hiworldwzj Collaborator Loading…
2
fix: correct 'Unsupport' typo to 'Unsupported' in error messages
#1320 opened May 25, 2026 by SuperMarioYL Loading…
13
update cpu cache load use async way.
#1318 opened May 25, 2026 by hiworldwzj Collaborator Loading…
3
support mtp for gemma4
#1316 opened May 22, 2026 by WANDY666 Contributor Loading…
4
fix: replace pickle deserialization with RestrictedUnpickler in PD WebSocket endpoints (CVE-2026-26220)
#1306 opened May 11, 2026 by nexadodigital Loading…
1
3
Propagate FINISHED_ERROR from detokenization init failure
#1299 opened May 9, 2026 by sufubao Collaborator Loading…
6 tasks
2
feat(RL): add RL support for verl
#1298 opened May 8, 2026 by shihaobai Collaborator Loading…
9
import flashqla to speedup gdn prefill
#1295 opened May 8, 2026 by WANDY666 Contributor Loading…
3
import flashqla and support cudagraph for gdn
#1292 opened May 6, 2026 by WANDY666 Contributor Loading…
3
ViT/multimodal token-budget admission + max_pixels clamp
#1290 opened May 6, 2026 by sufubao Collaborator Loading…
3 of 5 tasks
4
Logging colorization + access middleware cleanup + windowed cache stats
#1289 opened May 6, 2026 by sufubao Collaborator Loading…
6 tasks done
9
fix(api): forward extra_body.chat_template_kwargs on /v1/messages
#1276 opened Apr 18, 2026 by sufubao Collaborator Loading…
2 of 3 tasks
[Feature] Add support for Neo++
#1274 opened Apr 17, 2026 by XHPlus Contributor Loading…
3
【draft】Mtp optimization
#1266 opened Apr 9, 2026 by hiworldwzj Collaborator Loading…
6
fix error response format to match OpenAI API standard
#1259 opened Apr 7, 2026 by sufubao Collaborator Loading…
4 tasks
4
DRAFT: basic Profiler support and WIP hierarchical model level to op level profiling support
#1247 opened Apr 1, 2026 by WuSiYu Collaborator Loading…
8
feat: page size > 1 support
#1224 opened Mar 10, 2026 by blueswhen Collaborator Loading…
16
fix: implement RestrictedUnpickler to mitigate CVE-2026-26220
#1219 opened Mar 5, 2026 by RinZ27 Loading…
3
feat: add multi node disk cache
#1218 opened Mar 4, 2026 by blueswhen Collaborator Loading…
4
fix: patch CVE-2026-26220
#1217 opened Mar 3, 2026 by lucrbvi Loading…
7
ProTip! Filter pull requests by the default branch with base:main.