-
Notifications
You must be signed in to change notification settings - Fork 3.6k
Pull requests: sgl-project/sglang
Author
Label
Projects
Milestones
Reviews
Assignee
Sort
Pull requests list
[Bugfix] [NPU] bugfixes for running deepseek w4a8 quantization
deepseek
npu
#14542
opened Dec 6, 2025 by
iforgetmyname
•
Draft
6 tasks
[EPLB] Perf: optimize the balance packing with heap
deepseek
#14540
opened Dec 6, 2025 by
jinyouzhi
Loading…
1 of 6 tasks
[Misc]Register and refactor some environs for dpsk-fp4 and DeepEp
deepseek
documentation
Improvements or additions to documentation
run-ci
#14538
opened Dec 6, 2025 by
Fridge003
Loading…
6 tasks
fix: Handle spec_info length mismatch in Eagle Prefill/Extend phase
#14536
opened Dec 6, 2025 by
leavelet
Loading…
1 of 6 tasks
[Bug fix] Add /model_info endpoint to mini_lb
model-gateway
#14535
opened Dec 6, 2025 by
alisonshao
Loading…
1 task done
chore: upgrade cache-dit for better compatiblity
dependencies
Pull requests that update a dependency file
#14534
opened Dec 6, 2025 by
DefTruth
Loading…
feat(router): Add load-aware fallback to cache-aware policy
model-gateway
#14532
opened Dec 6, 2025 by
ppraneth
Loading…
6 tasks
[CI] Migrate Eagle 1-GPU tests to test/registered/
run-ci
#14529
opened Dec 6, 2025 by
alisonshao
Loading…
2 tasks
[CI] Add Mistral Large 3 Eagle basic PR test
run-ci
#14526
opened Dec 6, 2025 by
alisonshao
Loading…
[CI] Add Mistral Large 3 Eagle nightly performance test
#14525
opened Dec 6, 2025 by
alisonshao
Loading…
[Qwen3-next] remove heuristics and add radix cache kl test
run-ci
#14520
opened Dec 5, 2025 by
hanming-lu
Loading…
Debug amd diffusion
amd
dependencies
Pull requests that update a dependency file
diffusion
SGLang Diffusion
documentation
Improvements or additions to documentation
not-to-merge
run-ci
#14519
opened Dec 5, 2025 by
sunxxuns
Loading…
6 tasks
chore: bump sgl-kernel version to 0.3.18.post3
dependencies
Pull requests that update a dependency file
run-ci
#14518
opened Dec 5, 2025 by
sglang-bot
Loading…
[CI] Tiny speed up VLM CI
Multi-modal
multi-modal language model
run-ci
#14517
opened Dec 5, 2025 by
b8zhong
Loading…
[diffusion] pipeline: fix error when enable torch compile
diffusion
SGLang Diffusion
#14509
opened Dec 5, 2025 by
zcnrex
Loading…
6 tasks
[NPU][2/N] Ascend NPU quantization refactoring & more quantization formats support
#14504
opened Dec 5, 2025 by
OrangeRedeng
•
Draft
6 tasks
Optimize piecewise CUDA graph for Qwen3-Next
piecewise-cuda-graph
run-ci
#14502
opened Dec 5, 2025 by
Chen-0210
Loading…
2 tasks done
unified management of environment variables for vlm cuda ipc transport
run-ci
#14501
opened Dec 5, 2025 by
yhyang201
Loading…
6 tasks
[AMD] change fused rms quant interface for aiter upgrade
amd
deepseek
#14497
opened Dec 5, 2025 by
yctseng0211
•
Draft
6 tasks
[1/n] Fix hanging during DeepGemm Warmup
run-ci
#14493
opened Dec 5, 2025 by
Fridge003
Loading…
6 tasks
[Feature] Support file:// URL format for multimodal inputs
#14490
opened Dec 5, 2025 by
ppraneth
Loading…
6 tasks
Previous Next
ProTip!
Adding no:label will show everything without a label.