Skip to content

Pull requests: sgl-project/sglang

New pull request New
1,102 Open 9,862 Closed
1,102 Open 9,862 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

[model-gateway]: Implement hierarchical multi-tenant and model-based rate limiting model-gateway
#15517 opened Dec 20, 2025 by Ratish1 Loading…
4 of 6 tasks
1
[model-gateway] Support MCP Namespaces model-gateway run-ci
#15516 opened Dec 20, 2025 by xuwenyihust Loading…
2 of 6 tasks
1
[model-gateway] Optimize WASM Runtime with Instance Pooling and Component Caching model-gateway
#15515 opened Dec 20, 2025 by ppraneth Loading…
6 tasks
1
Add Flashinfer DeepGEMM SM90 for SwapAB Optimization
#15514 opened Dec 20, 2025 by b8zhong Loading…
6 tasks done
1
feature: support unicorn access log filter(disable logging /metrics)
#15513 opened Dec 20, 2025 by alphabetc1 Loading…
6 tasks
1
[Feature] overlap LoRA weight loading with compute
#15512 opened Dec 20, 2025 by glenliu21 Loading…
4 of 6 tasks
1
[Diffusion] Wan video model support zero-cost weight offload and overlap with compute diffusion SGLang Diffusion
#15511 opened Dec 20, 2025 by BBuf Loading…
6 tasks
7
Clean up logprob utils run-ci
#15509 opened Dec 20, 2025 by hnyls2002 Loading…
2
fix(qwen_vl): add semaphore to serialize video decoding for thread safety
#15506 opened Dec 20, 2025 by ShuhangGe Loading…
1
chore: bump sgl-kernel version to 0.3.20 amd dependencies Pull requests that update a dependency file run-ci sgl-kernel
#15501 opened Dec 19, 2025 by sglang-bot Loading…
2
[AMD] Add nightly performance benchmark tests amd deepseek
#15500 opened Dec 19, 2025 by michael-amd • Draft
6 tasks
1
Draft: MLA Eagle3 deepseek
#15499 opened Dec 19, 2025 by IzzyPutterman Loading…
6 tasks
2
feat: only add input vision tokens in bench_serving result if vision dataset is used
#15492 opened Dec 19, 2025 by raayandhar Loading…
6 tasks done
6
[MiMoV2Flash] fix: respect --swa-full-tokens-ratio arg run-ci
#15488 opened Dec 19, 2025 by acelyc111 Loading…
6 tasks
5
[WIP] MLP weight prefetching unification
#15482 opened Dec 19, 2025 by terfendail • Draft
6 tasks
@ping1jing2
6
[diffusion] kernel: support qk rotary_embedding in one triton kernel diffusion SGLang Diffusion
#15480 opened Dec 19, 2025 by triple-Mu Loading…
6 tasks
4
[diffusion] refactor: support scheduling logic for reqs inside scheduler diffusion SGLang Diffusion
#15479 opened Dec 19, 2025 by mickqian Loading…
6 tasks
4
tiny fix: fix glm46v launch and transformers issue
#15476 opened Dec 19, 2025 by yhyang201 Loading…
6 tasks
3
[WIP][EPD][VLM] support video input(qwen-series)
#15475 opened Dec 19, 2025 by ZhengWG Loading…
6 tasks
4
Fix reasoning parser in non-stream
#15472 opened Dec 19, 2025 by mingMelody Loading…
6 tasks
1
1
[sgl-kernel][6/7]Support Expert Specialization Grouped GEMM sgl-kernel
#15471 opened Dec 19, 2025 by HydraQYH Loading…
1 of 6 tasks
5
Fix 'Scheduler' object has no attribute 'port_args' error
#15470 opened Dec 19, 2025 by lambert0312 Loading…
1 of 6 tasks
3
Fix Illegal Memory Access when fa3 + spec + topk + page_size > 1
#15469 opened Dec 19, 2025 by yubofredwang Loading…
6 tasks
7
[Quantization]feat: Add Nvidia ModelOpt HF FP8 support for fp8_pc_pt and fp8_pb_wo documentation Improvements or additions to documentation quant LLM Quantization
#15468 opened Dec 19, 2025 by CedricHwong Loading…
4 of 6 tasks
1
@Edwardf0t1
3
Add similar to vllm wait --ready-check-timeout-sec parameter for benchmark script
#15466 opened Dec 19, 2025 by almaslof Loading…
4
ProTip! Add no:assignee to see everything that’s not assigned.