Skip to content

Pull requests: sgl-project/sglang

New pull request New
22 Open 1,399 Closed
22 Open 1,399 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

[Performance]: Process affinity to CPU cores with multiple sockets support
#2171 opened Nov 25, 2024 by HaiShaw Loading…
Replace prob based with threshold based load balancing
#2170 opened Nov 25, 2024 by ByronHsu Loading…
3 tasks done
test select concurrency
#2165 opened Nov 24, 2024 by qeternity Loading…
Speculative EAGLE2. New PR
#2150 opened Nov 24, 2024 by yukavio Loading…
13
Byhsu/fairness router
#2149 opened Nov 24, 2024 by ByronHsu • Draft
3 tasks
[Draft] Resolving integration differences after XGrammar lauch refactoring
#2145 opened Nov 23, 2024 by gittb • Draft
3 tasks
15
add profile in offline benchmark & update doc await-response
#2123 opened Nov 22, 2024 by bjmsong Loading…
3 tasks
5
Online weight update [WIP]
#2119 opened Nov 22, 2024 by zhaochenyang20 • Draft
3 tasks
4
feat: use cascade attention kernel (single level)
#2101 opened Nov 20, 2024 by james-p-xu • Draft
1 of 3 tasks
2
feat(srt): support prefill and generate with input_embeds
#2082 opened Nov 18, 2024 by XuehaiPan • Draft
1 of 3 tasks
1
12
Add log input text when using openai chat api await-response
#2058 opened Nov 17, 2024 by ccjincong Loading…
3 tasks done
8
[TEST] flashinfer version upgrade to v0.2.0
#2054 opened Nov 17, 2024 by james-p-xu • Draft
3 tasks
9
Input_embeds support await-response high priority
#2052 opened Nov 16, 2024 by RinRin-32 Loading…
1 of 3 tasks
11
Add support for GPT-J
#2041 opened Nov 15, 2024 by danilotpnta • Draft
1
regex stopping condition
#2035 opened Nov 14, 2024 by jancervenka Loading…
3 tasks done
7
[WIP] Use FlashInfer RoPE
#2016 opened Nov 12, 2024 by james-p-xu Loading…
3 tasks done
2
Add model support for Phi 3.5 MoE await-response
#1948 opened Nov 7, 2024 by svaruag • Draft
3 tasks
@merrymercy
3
Debug studio await-response
#1831 opened Oct 29, 2024 by zolinthecow Loading…
3 tasks done
@ByronHsu
7
Granite and GraniteMoE models. await-response
#1818 opened Oct 27, 2024 by janimo • Draft
@merrymercy
2
Surpport kv cache int8/int4 for triton backend await-response
#1644 opened Oct 12, 2024 by yuguo-Jack Loading…
@merrymercy
17
[Feature] Add initial support for sequence parallelism
#1436 opened Sep 16, 2024 by Ying1123 • Draft
@Ying1123
Function calling for OpenAI backend
#573 opened Jun 29, 2024 by Yiyun-Liang Loading…
@Ying1123
19
ProTip! Updated in the last three days: updated:>2024-11-21.