Skip to content

Pull requests: sgl-project/sglang

New pull request New
394 Open 4,454 Closed
394 Open 4,454 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
Assigned to nobody Loading
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Pull requests list

refactor(test): reorganize OpenAI test file structure
#7408 opened Jun 21, 2025 by CatherineSue Loading…
2 of 6 tasks
3
Tiny add logging for GC
#7406 opened Jun 21, 2025 by fzyzcjy Loading…
6 tasks
4
Tiny fix two-batch overlap incompatible with new DeepGEMM
#7405 opened Jun 21, 2025 by fzyzcjy Loading…
6 tasks
3
Fix prefill OOM due to wrong token calculation when page > 1
#7397 opened Jun 20, 2025 by hnyls2002 Loading…
1
3
[BugFix]: fix EmbeddingReqInput single input error
#7396 opened Jun 20, 2025 by woodx9 Loading…
1 of 6 tasks
3
[BugFix]fix qwen25 invoke function call streaming responses with curly braces as the starting indicator
#7394 opened Jun 20, 2025 by ehuaa Loading…
6 tasks
4
[Quantization] Add int4fp8_moe online quantization on ROCm
#7392 opened Jun 20, 2025 by fxmarty-amd • Draft
6 tasks
9
Fix torch compile run aiter AI Tensor Engine ROCm bug Something isn't working
#7391 opened Jun 20, 2025 by kkHuang-amd Loading…
5 tasks
3
Add V2-lite model test
#7390 opened Jun 20, 2025 by yanbing-j • Draft
6 tasks
8
npu fused op
#7386 opened Jun 20, 2025 by ll819214 Loading…
6 tasks
5
feat: make send/recv DtoD and async
#7385 opened Jun 20, 2025 by TianyuZhang1214 • Draft
6 tasks
9
fix gpu_id_step
#7384 opened Jun 20, 2025 by TomQuartz Loading…
1 of 6 tasks
3
enable ptpc gemm_a8w8_bpreshuffle_CK form rocm aliter
#7383 opened Jun 20, 2025 by Yuechguo Loading…
6 tasks done
5
kvcache io kernels and test case
#7382 opened Jun 20, 2025 by xiezhq-hermann Loading…
2 of 6 tasks
8
[feat] support minimum token load balance in dp attention
#7379 opened Jun 20, 2025 by WANG-GH Loading…
2 of 3 tasks
9
Quick fix for DeepGemm requant to also cover MTP. high priority
#7378 opened Jun 20, 2025 by pyc96 Loading…
6 tasks
@zhyncs
4
Fix MTP with Deepseek R1 Fp4 bug Something isn't working high priority
#7376 opened Jun 20, 2025 by pyc96 Loading…
6 tasks
@zhyncs
7
Reduce overhead for fa by not calling heavy CUDA property check
#7375 opened Jun 20, 2025 by oraluben Loading…
1 of 6 tasks
3
[Feature] Radix Tree in C++
#7369 opened Jun 20, 2025 by DarkSharpness Loading…
1 of 6 tasks
9
[Fix] Correctly set head_dim fallback
#7368 opened Jun 19, 2025 by p12tic Loading…
1 of 6 tasks
2
[WIP] SWA Prefix Cache
#7367 opened Jun 19, 2025 by hanming-lu • Draft
6 tasks
8
[misc] Add PD service discovery support in router high priority
#7361 opened Jun 19, 2025 by slin1237 Loading…
3 of 6 tasks
@hnyls2002 @ShangmingCai
20
Support Npu graph executor high priority
#7359 opened Jun 19, 2025 by joozhan Loading…
6 tasks
@Alcanderian
19
feat(oai refactor): Remove openai_api with entrypoints/openai collaboration high priority
#7351 opened Jun 19, 2025 by CatherineSue Loading…
2 of 6 tasks
@CatherineSue @zhyncs @jhinpan
18
fix stop_str bug
#7347 opened Jun 19, 2025 by huangtingwei9988 Loading…
6 tasks
4
ProTip! no:milestone will show everything without a milestone.