Skip to content

Pull requests: sgl-project/sglang

New pull request New
16 Open 1,244 Closed
16 Open 1,244 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
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Pull requests list

Fix metrics
#1963 opened Nov 8, 2024 by binarycrayon Loading…
2 of 3 tasks
2
Add model support for Phi 3.5 MoE await-response
#1948 opened Nov 7, 2024 by svaruag • Draft
3 tasks
@merrymercy
2
[rust] cache-aware DP - approx tree high priority
#1934 opened Nov 6, 2024 by ByronHsu Loading…
3 tasks done
@Ying1123
5
Instructions on Profiling SGLang Infer System with AMD GPUs await-response
#1929 opened Nov 5, 2024 by leishaoSC Loading…
2 of 3 tasks
11
Scheduler methods high priority
#1913 opened Nov 4, 2024 by josephydu Loading…
@ByronHsu
21
[Draft] Add Tensor Parallel to torch_native_llama
#1876 opened Nov 2, 2024 by kwen2501 • Draft
3 tasks
5
chore: update torch v2.5.1
#1849 opened Oct 31, 2024 by zhyncs • Draft
3 tasks
3
Debug studio
#1831 opened Oct 29, 2024 by zolinthecow Loading…
3 tasks done
2
Granite and GraniteMoE models. await-response
#1818 opened Oct 27, 2024 by janimo • Draft
@merrymercy
2
Introducing SGLang Guru on Gurubase.io await-response
#1745 opened Oct 21, 2024 by kursataktas Loading…
7
[LoRA, Performance] Add gemm expand triton kernel for multi-LoRA
#1728 opened Oct 20, 2024 by Ying1123 • Draft
4 of 15 tasks
Surpport kv cache int8/int4 for triton backend high priority
#1644 opened Oct 12, 2024 by yuguo-Jack Loading…
17
[WIP] Support NVLM-D
#1601 opened Oct 7, 2024 by amosyou • Draft
3 tasks
1
[WIP] Spec infer with EAGLE2
#1498 opened Sep 24, 2024 by yukavio Loading…
3 tasks
41
[Feature] Add initial support for sequence parallelism
#1436 opened Sep 16, 2024 by Ying1123 • Draft
Function calling for OpenAI backend
#573 opened Jun 29, 2024 by Yiyun-Liang Loading…
@Ying1123
19
ProTip! Add no:assignee to see everything that’s not assigned.