Skip to content

Pull requests: sgl-project/sglang

New pull request New
36 Open 1,801 Closed
36 Open 1,801 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

Cache controller for hierarchical caching
#2804 opened Jan 9, 2025 by xiezhq-hermann Loading…
2 of 3 tasks
[WIP] [Feature] Support Deepseek-VL2 enhancement New feature or request
#2798 opened Jan 8, 2025 by ccw1996 • Draft
3 tasks
@yizhang2077 @ispobock @zhyncs
3
Add endpoint for file support, purely to speed up processing of input_embeds.
#2797 opened Jan 8, 2025 by RinRin-32 Loading…
1 of 3 tasks
Allow multi SGLang engines to coordinate
#2791 opened Jan 8, 2025 by fzyzcjy Loading…
3 tasks done
Speculative decoding with lookahead enhancement New feature or request
#2790 opened Jan 8, 2025 by jjjjohnson Loading…
3 tasks done
@merrymercy @yukavio
1
[Doc] Deepseek reference docs
#2787 opened Jan 8, 2025 by XiaotongJiang Loading…
3 tasks done
13
Support FP8 E4M3 KV Cache
#2786 opened Jan 8, 2025 by bjmsong Loading…
3 tasks
[Feature] Support minicpmv v2.6
#2785 opened Jan 8, 2025 by mickqian Loading…
3 tasks done
2
Refactor Engine, API server and dispatching
#2747 opened Jan 6, 2025 by fzyzcjy Loading…
3 tasks done
Update doc for server arguments
#2742 opened Jan 5, 2025 by simveit • Draft
1 task
47
Benchmark results for DeepSeek-v3 in 2x8xH200 Cluster
#2738 opened Jan 5, 2025 by roG0d Loading…
1 of 3 tasks
4
[Eagle2]Fix multiple concurrent request crashes
#2730 opened Jan 4, 2025 by coolhok Loading…
3 tasks done
@merrymercy @yukavio
5
WIP: Feature/function calling update
#2700 opened Jan 2, 2025 by YAMY1234 Loading…
9
[Feature] Support regex as a stopping condition
#2699 opened Jan 2, 2025 by mickqian Loading…
3 tasks done
Hierarchical Caching for SGLang enhancement New feature or request
#2693 opened Jan 1, 2025 by xiezhq-hermann Loading…
3 tasks
@Ying1123
5
Online serving benchmarks [multiturn chat, shared prefix] to multi-tier KV caching
#2665 opened Dec 30, 2024 by PanJason Loading…
5 tasks
@xiezhq-hermann
2
CUDA-graph-compatible releasing and resuming KV cache and model weight memory
#2630 opened Dec 28, 2024 by fzyzcjy Loading…
3 tasks done
3
Support InternVL2 Series
#2629 opened Dec 28, 2024 by amosyou • Draft
3 of 7 tasks
2
[Feature] support TransformerEngine to enable communication overlap
#2627 opened Dec 28, 2024 by Zhuohao-Li • Draft
2 of 6 tasks
Refactor Scheduler to improve code organization
#2593 opened Dec 26, 2024 by libratiger Loading…
3 tasks done
3
[Feature] Add partial support for parrallel_tool_calls in Funcation Calling API
#2576 opened Dec 25, 2024 by HaoyuWang4188 Loading…
3 tasks done
@Ying1123
6
[Docs] add quantization docs dependencies Pull requests that update a dependency file
#2572 opened Dec 25, 2024 by JamesSand Loading…
3 tasks done
@HandH1998 @zhyncs @zhaochenyang20
48
[Cache Offload] Improve radix cache offload benchmark
#2534 opened Dec 20, 2024 by Edenzzzz • Draft
3 tasks
@xiezhq-hermann
1
[Cache Offload] Remove device sync overhead
#2533 opened Dec 20, 2024 by Edenzzzz Loading…
3 tasks
@xiezhq-hermann
adapt custom allreduce for tensorrt llm high priority
#2511 opened Dec 18, 2024 by yizhang2077 Loading…
3 tasks
@zhyncs
9
ProTip! Adding no:label will show everything without a label.