-
Notifications
You must be signed in to change notification settings - Fork 3.4k
Pull requests: sgl-project/sglang
Pull requests list
Install a github action lint in pre-commit
amd
run-ci
#13467
opened Nov 18, 2025 by
Kangyan-Zhou
Loading...
[Piecewise CUDA Graph] Support Kimi-K2 (non-Thinking)
run-ci
#13466
opened Nov 18, 2025 by
b8zhong
Loading...
Expend compatibility check for all quantized MoE models
run-ci
#13465
opened Nov 18, 2025 by
JustinTong0323
Loading...
5 tasks
Adding CI Monitor Improvements
documentation
Improvements or additions to documentation
#13462
opened Nov 17, 2025 by
dougyster
Loading...
Fix NFS EBUSY error in PR test workflow
run-ci
#13460
opened Nov 17, 2025 by
alisonshao
Loading...
3 tasks done
[Deepseek V3.2] Change indexer weights_proj to fp32
deepseek
documentation
Improvements or additions to documentation
#13459
opened Nov 17, 2025 by
hlu1
Loading...
5 tasks
[Feature] Introduce JIT Kernel in sglang (with hicache JIT kernel)
hicache
Hierarchical Caching for SGLang
run-ci
#13453
opened Nov 17, 2025 by
DarkSharpness
Loading...
5 tasks
[AMD CI] Local cache fallback.
amd
run-ci
#13452
opened Nov 17, 2025 by
saienduri
Loading...
5 tasks
[WIP][Quantization] fix: fix gguf moe model inference
dependencies
Pull requests that update a dependency file
run-ci
sgl-kernel
#13451
opened Nov 17, 2025 by
FlamingoPg
Loading...
2 of 9 tasks
[3/N] CI refactor: move some manually triggered tests.
documentation
Improvements or additions to documentation
Multi-modal
multi-modal language model
#13448
opened Nov 17, 2025 by
hnyls2002
Loading...
[Minor] support log (load/write) bandwidth for hicache
run-ci
#13446
opened Nov 17, 2025 by
DarkSharpness
Loading...
5 tasks
[CI] re-enable test_vision_openai_server_a ci
Multi-modal
multi-modal language model
run-ci
#13444
opened Nov 17, 2025 by
yhyang201
Loading...
5 tasks
[Feature]Introduce DeepEP's Per-Expert-overlap(PEO) capability into SGLang.
quant
LLM Quantization
#13442
opened Nov 17, 2025 by
zhihui1084
•
Draft
5 tasks
[WEIGHT LOADER] Add support for
serverless_llm format loader
run-ci
#13440
opened Nov 17, 2025 by
JustinTong0323
Loading...
5 tasks
[Bug] Fixes accuracy issues caused by incorrect use of rope
#13439
opened Nov 17, 2025 by
Paiiiiiiiiiiiiii
Loading...
5 tasks
[Feat] Add created time in serving_base
#13432
opened Nov 17, 2025 by
zhanghaotong
Loading...
1 of 5 tasks
Delete aarch64 below SM90 condition
run-ci
sgl-kernel
#13430
opened Nov 17, 2025 by
johnnynunez
Loading...
5 tasks done
Support external custom models
Multi-modal
multi-modal language model
#13429
opened Nov 17, 2025 by
zhooooong
Loading...
2 of 5 tasks
[Feat][NVFP4] Enable NVFP4 MoE for Qwen series models (eg. Qwen3-Next)
#13427
opened Nov 17, 2025 by
samuellees
Loading...
1 of 7 tasks
feat: Support Spec V2 + Constrained Decoding
#13425
opened Nov 17, 2025 by
Ubospica
Loading...
5 tasks
[SPEC_V2] Optimize _draft_extend_for_prefill by Replacing Python Copy Loop with Triton Kernel
run-ci
#13424
opened Nov 17, 2025 by
YAMY1234
Loading...
5 tasks
EPLB: Improve compute_logical_to_rank_dispatch_physical_map efficiency and balance
#13423
opened Nov 17, 2025 by
doo28x
Loading...
5 tasks
[MultiModal]Support stable-diffusion-3-medium-diffusers
run-ci
#13422
opened Nov 17, 2025 by
IPostYellow
Loading...
5 tasks
ProTip!
Type g i on any issue or pull request to go back to the issue listing page.
You can’t perform that action at this time.