Skip to content

Pull requests: sgl-project/sglang

New pull request New
41 Open 1,654 Closed
41 Open 1,654 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

[Feature] Streaming API for Function Calling
#2576 opened Dec 25, 2024 by HaoyuWang4188 • Draft
3 tasks
[unittest] add unit test to test quant args of srt engine
#2574 opened Dec 25, 2024 by JamesSand Loading…
3 tasks done
[Docs] add quantization docs
#2572 opened Dec 25, 2024 by JamesSand Loading…
3 tasks done
19
Refactor SchedulePolicy to improve code organization
#2571 opened Dec 25, 2024 by libratiger Loading…
3 tasks done
2
[UTILS] improve makefile a bit by adding help info
#2570 opened Dec 24, 2024 by kzhou003 • Draft
3 tasks
Fix duplicated handling of GetWeightsByNameReqInput
#2565 opened Dec 24, 2024 by fzyzcjy Loading…
3 tasks
Super tiny typo fix
#2564 opened Dec 24, 2024 by fzyzcjy Loading…
3 tasks
h100 tuning fused_moe_triton for qwen2 moe
#2560 opened Dec 23, 2024 by BBuf Loading…
3 tasks done
1
Error occurs when loading the gemma model in bitsandbytes format.
#2557 opened Dec 23, 2024 by upskyy Loading…
1 of 3 tasks
Fix cache hit rate when chunked prefill
#2555 opened Dec 23, 2024 by hnyls2002 Loading…
Fix packet loss when deploy little model
#2548 opened Dec 23, 2024 by sdli1995 • Draft
3 tasks
feat:support 2 kenrels for mixed chunked prefill
#2546 opened Dec 22, 2024 by chosen-ox Loading…
2 tasks
[Feature] Function Tooling
#2544 opened Dec 22, 2024 by Tushar-ml Loading…
2 of 3 tasks
4
Enable Nvidia's ModelOpt fp8 quantized models await-response
#2535 opened Dec 21, 2024 by Edwardf0t1 Loading…
3 tasks
4
[Cache Offload] Improve radix cache offload benchmark
#2534 opened Dec 20, 2024 by Edenzzzz • Draft
3 tasks
[Cache Offload] Remove device sync overhead
#2533 opened Dec 20, 2024 by Edenzzzz Loading…
3 tasks
[Feature] Support new parameter - EBNF in xgrammar
#2526 opened Dec 19, 2024 by adarshxs Loading…
2 of 3 tasks
8
fix: package data missing
#2521 opened Dec 19, 2024 by yudian0504 Loading…
Add generator-style run_batch function
#2513 opened Dec 18, 2024 by xingyaoww Loading…
1
3
adapt custom allreduce for tensorrt llm high priority
#2511 opened Dec 18, 2024 by yizhang2077 Loading…
3 tasks
@zhyncs
7
fix: add ninja as dependency for flashinfer v0.2
#2501 opened Dec 17, 2024 by zhyncs • Draft
3 tasks
1
torcho gemlite integration
#2498 opened Dec 17, 2024 by HDCharles Loading…
3 tasks
improve performance by removing use_tensor_core dependency await-response
#2496 opened Dec 17, 2024 by bjmsong Loading…
3 tasks
2
[Experimental] Add a gRPC server for completion request high priority
#2478 opened Dec 13, 2024 by MrAta Loading…
2 of 3 tasks
@Ying1123
9
[FIX] Update EOS from config await-response
#2475 opened Dec 13, 2024 by zhengy001 Loading…
1 of 3 tasks
3
ProTip! Type g p on any issue or pull request to go back to the pull request listing page.