-
Notifications
You must be signed in to change notification settings - Fork 5.4k
Pull requests: sgl-project/sglang
Author
Label
Projects
Milestones
Reviews
Assignee
Sort
Pull requests list
[WIP] sglang miles lora
deepseek
jit-kernel
lora
quant
LLM Quantization
#23065
opened Apr 17, 2026 by
yushengsu-thu
Collaborator
Loading…
5 tasks
[bugfix]fix(qwen3_5): broadcast per-tensor scale in _make_packed_weight_loader for FP8 models
#23062
opened Apr 17, 2026 by
kkyyxhll
Loading…
3 of 5 tasks
[fix] Fix dynamic chunking profiling crash on GLM-5 models
#23060
opened Apr 17, 2026 by
Baichuan7
Loading…
feat(hip): add optional external LLMM1 fast path
quant
LLM Quantization
#23059
opened Apr 17, 2026 by
skyguan92
Loading…
[Diffusion][NPU][CI] update perf numbers
diffusion
SGLang Diffusion
npu
run-ci
#23056
opened Apr 17, 2026 by
Makcum888e
Contributor
Loading…
5 tasks
Add test cases for NPU runtime_options feature
npu
#23054
opened Apr 17, 2026 by
Sugar920
Contributor
Loading…
5 tasks
[CI] Exclude diffusion-specific paths from main_package filter
#23053
opened Apr 17, 2026 by
LLThomas
Contributor
Loading…
2 of 5 tasks
[Diffusion] Diffusion model support log-requests
diffusion
SGLang Diffusion
#23049
opened Apr 17, 2026 by
LLThomas
Contributor
Loading…
3 of 5 tasks
[Scheduler] Allow chunked requests to fill tail chunk budget in prefill batch
#23048
opened Apr 17, 2026 by
Baichuan7
Loading…
[Lora] Support LoRA and multi-batch in bench_one_batch_server
documentation
Improvements or additions to documentation
run-ci
[AMD] Fix AMD Multimodal Test - skip nvfp4 tests
diffusion
SGLang Diffusion
#23045
opened Apr 17, 2026 by
yctseng0211
Collaborator
Loading…
7 tasks
[XPU] Fix DeepSeek-OCR tests under transformers 5.x
deepseek
run-ci
#23044
opened Apr 17, 2026 by
JustinTong0323
Collaborator
Loading…
2 tasks
[HiCache] fix: add capability guard for HiCache storage v2
hicache
Hierarchical Caching for SGLang
#23043
opened Apr 17, 2026 by
alphabetc1
Collaborator
Loading…
5 tasks
Re-export network utilities from sglang.srt.utils package
#23042
opened Apr 17, 2026 by
singhalshubham03
Contributor
Loading…
3 tasks done
Revert "perf: optimize PCG inductor path for FP8 models (#21734)"
run-ci
#23039
opened Apr 17, 2026 by
bingxche
Collaborator
Loading…
1 task
[KDA] Fuse gate+cumsum and reuse chunk index for KDA
run-ci
#23038
opened Apr 17, 2026 by
yuan-luo
Collaborator
Loading…
5 tasks
[GLM-5.1] Use clone for logits output for MTP layers
#23037
opened Apr 17, 2026 by
zRzRzRzRzRzRzR
Contributor
Loading…
[test] Add unit tests for Qwen25Detector (#20865)
#23030
opened Apr 17, 2026 by
Spectual
Loading…
4 tasks
fix: add explicit barrier for DP-attention in scheduler to prevent race conditions
run-ci
#23027
opened Apr 17, 2026 by
AndyLi429
Loading…
5 tasks done
Optimize LTX2 modulation and two-stage warmup
diffusion
SGLang Diffusion
lora
#23025
opened Apr 17, 2026 by
BBuf
Collaborator
Loading…
fix: support Anthropic web_search built-in tools in /v1/messages
#23024
opened Apr 17, 2026 by
he-yufeng
Contributor
Loading…
3 tasks
ci: add stage-a gate for multimodal-gen PR tests
diffusion
SGLang Diffusion
Multi-modal
multi-modal language model
run-ci
#23023
opened Apr 17, 2026 by
mickqian
Collaborator
Loading…
2 of 3 tasks
Add test cases for NPU scenarios.
npu
run-ci
#23021
opened Apr 17, 2026 by
liuxianglong17
Loading…
5 tasks done
Previous Next
ProTip!
Type g i on any issue or pull request to go back to the issue listing page.