Skip to content

Pull requests: ModelTC/LightLLM

New pull request New
33 Open 883 Closed
33 Open 883 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 triton autotuner fallback logic
#1148 opened Dec 15, 2025 by flyinglandlord Loading…
3
add gsmk test script
#1136 opened Dec 5, 2025 by sufubao Loading…
10
add launch_server and StartArgs (#1119)
#1135 opened Dec 5, 2025 by sufubao Loading…
4
Qwen3 moe mtp
#1131 opened Dec 2, 2025 by shihaobai Loading…
7
Add top_logprobs Support
#1124 opened Nov 24, 2025 by ahmadbasyouni10 Loading…
8
feat(misc): Profiler support
#1121 opened Nov 20, 2025 by WuSiYu Loading…
16
Support Qwen3next and prefix cache.
#1115 opened Nov 18, 2025 by sufubao Loading…
5
add flashinfer fused_norm_add op
#1105 opened Nov 13, 2025 by SangChengC Loading…
14
support Deepseek3.2
#1103 opened Nov 10, 2025 by sufubao Loading…
8
add flashinfer-trtllm-ragged-prefill-attn
#1099 opened Nov 6, 2025 by SangChengC Loading…
3
Add qwen3 vl
#1095 opened Nov 4, 2025 by SangChengC Loading…
17
fix: MTP in chunked prefill mode
#1079 opened Oct 14, 2025 by sufubao Loading…
3
support interns1
#1060 opened Sep 18, 2025 by xhx1022 Loading…
12
enable fa3 and fused_shared_experts by default
#1053 opened Sep 15, 2025 by sufubao Loading…
4
fix tl.where and set the default loader worker number
#1052 opened Sep 11, 2025 by sufubao Loading…
feat: Implementing Past Future Scheduler
#1048 opened Sep 8, 2025 by WuSiYu Loading…
Optimize multimodal resource allocation with concurrency and improved batch RPC
#1017 opened Aug 21, 2025 by dyyoungg Loading…
[support] vit and llm disaggregation
#1014 opened Aug 20, 2025 by SangChengC Loading…
add fa3_mtp
#1005 opened Aug 11, 2025 by WANDY666 Loading…
8
Support Qwen models' dp>1 in PD
#999 opened Aug 5, 2025 by zhhangBian Loading…
4
add rmsnorm-add fusion kernel
#996 opened Aug 4, 2025 by theNiemand Loading…
8
Asynchicache
#977 opened Jul 21, 2025 by jinbiaoyu Loading…
13
Fp8 deepseek
#975 opened Jul 17, 2025 by blueswhen Loading…
4
cuda graph pool with LRU
#964 opened Jul 8, 2025 by STwangyingrui Loading…
10
Add fake balance for EP mode
#962 opened Jul 8, 2025 by STwangyingrui Loading…
3
ProTip! Exclude everything labeled bug with -label:bug.