Skip to content

Pull requests: sgl-project/sglang

New pull request New
35 Open 1,741 Closed
35 Open 1,741 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

Speed up update_weights_from_tensor
#2695 opened Jan 1, 2025 by fzyzcjy Loading…
3 tasks
1
Hierarchical Caching for SGLang enhancement New feature or request
#2693 opened Jan 1, 2025 by xiezhq-hermann Loading…
3 tasks
1
Support twoshot kernel
#2688 opened Dec 31, 2024 by yizhang2077 Loading…
3 tasks
@zhyncs
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
[feat] Add math eval to CI nightly run
#2663 opened Dec 30, 2024 by XiaotongJiang Loading…
3
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
[Feature] support TransformerEngine to enable communication overlap
#2627 opened Dec 28, 2024 by Zhuohao-Li • Draft
2 of 6 tasks
[Feature, Hardware] Enable DeepseekV3 on AMD GPUs amd bug Something isn't working high priority
#2601 opened Dec 26, 2024 by BruceXcluding • Draft
9 tasks
@ispobock @HandH1998 @zhyncs
60
Refactor Scheduler to improve code organization
#2593 opened Dec 26, 2024 by libratiger Loading…
3 tasks done
3
[Feature] Streaming API for Function Calling
#2576 opened Dec 25, 2024 by HaoyuWang4188 • Draft
3 tasks
@Ying1123
1
[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
42
Refactor SchedulePolicy to improve code organization
#2571 opened Dec 25, 2024 by libratiger Loading…
3 tasks done
@hnyls2002
4
Fix packet loss when deploy little model high priority
#2548 opened Dec 23, 2024 by sdli1995 • Draft
3 tasks
@merrymercy
1
feat:support 2 kenrels for mixed chunked prefill
#2546 opened Dec 22, 2024 by chosen-ox Loading…
2 tasks
@hnyls2002
3
Enable Nvidia's ModelOpt fp8 quantized models high priority quant LLM Quantization
#2535 opened Dec 21, 2024 by Edwardf0t1 Loading…
1 of 3 tasks
@ispobock @zhyncs
7
[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
Add generator-style run_batch function await-response
#2513 opened Dec 18, 2024 by xingyaoww Loading…
1
@merrymercy
5
adapt custom allreduce for tensorrt llm high priority
#2511 opened Dec 18, 2024 by yizhang2077 Loading…
3 tasks
@zhyncs
9
fix: add ninja as dependency for flashinfer v0.2 flashinfer high priority
#2501 opened Dec 17, 2024 by zhyncs • Draft
3 tasks
@zhyncs
1
improve performance by removing use_tensor_core dependency await-response
#2496 opened Dec 17, 2024 by bjmsong Loading…
3 tasks
@merrymercy
8
[Experimental] Add a gRPC server for completion request high priority
#2478 opened Dec 13, 2024 by MrAta Loading…
2 of 3 tasks
@Ying1123
21
Add InfiniteBench for long context benchmarking high priority
#2421 opened Dec 9, 2024 by iankur Loading…
2 of 3 tasks
@zhyncs
9
[Feature] Add sampler custom logits processor
#2396 opened Dec 8, 2024 by hongpeng-guo Loading…
2 of 3 tasks
@merrymercy
5
ProTip! Updated in the last three days: updated:>2024-12-29.