Skip to content

Pull requests: sgl-project/sglang

New pull request New
842 Open 8,499 Closed
842 Open 8,499 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

[10/n] decouple quantization impl from vllm dependency - fix import format Auto Format Code run-ci
#13524 opened Nov 18, 2025 by FlamingoPg Loading…
1 of 6 tasks
@AniZpZ @FlamingoPg
3
Fixing hooks test by adding more realistic hook module to import
#13523 opened Nov 18, 2025 by Carlomus Loading…
3
fix double Unicode escape issue in streaming tool_calls parameters
#13518 opened Nov 18, 2025 by lw9527 Loading…
6 tasks
4
add speculative args checking run-ci speculative-decoding
#13517 opened Nov 18, 2025 by QsingHuan Loading…
5
Fix TorchAO quant in VLM
#13508 opened Nov 18, 2025 by zhooooong Loading…
2 of 5 tasks
4
Shortest-extend-length scheduling policy documentation Improvements or additions to documentation
#13507 opened Nov 18, 2025 by totktospit Loading…
3 of 5 tasks
modularize gsm8k and mmmu test classes Multi-modal multi-modal language model run-ci
#13506 opened Nov 18, 2025 by netanel-haber Loading…
2 tasks done
@yhyang201
7
[Draft][feat] sglang auto tuner cli
#13505 opened Nov 18, 2025 by LuYanFCP Loading…
1 of 5 tasks
7
[Docs] Add doc for expert parallelism (EP) documentation Improvements or additions to documentation
#13504 opened Nov 18, 2025 by YinglingWang Loading…
2 of 5 tasks
5
update model_test deepseek Multi-modal multi-modal language model
#13502 opened Nov 18, 2025 by hhhh1252023 Loading…
5 tasks
8
debug testcase Multi-modal multi-modal language model
#13500 opened Nov 18, 2025 by htj827 Loading…
5 tasks
9
fix: check HF_HUB_OFFLINE before fetching remote hf_quant_config.json
#13499 opened Nov 18, 2025 by lwabish Loading…
1 of 5 tasks
2
[HiCache] fix unit test with changed new APIs run-ci
#13498 opened Nov 18, 2025 by stmatengss Loading…
5 tasks
@xiezhq-hermann
4
[Bug] Fixes accuracy issues caused by incorrect use of rope
#13495 opened Nov 18, 2025 by Baidu-AIAK Loading…
5 tasks
1
[Intel XPU]Add xpu profiler support for one batch benchmarking
#13494 opened Nov 18, 2025 by gaopengff • Draft
CI: improve diffusion CI run-ci
#13493 opened Nov 18, 2025 by mickqian Loading…
5 tasks
1
[Diffusion] add rocm support. amd
#13492 opened Nov 18, 2025 by sabreshao Loading…
5 tasks
1
[Tiny ci fix] Fix test isolation issues in test_model_hooks.py run-ci
#13490 opened Nov 18, 2025 by BBuf Loading…
5 tasks
6
Flashinfer TRTLLM-GEN-MoE + Qwen3 run-ci
#13489 opened Nov 18, 2025 by b8zhong Loading…
9
fix: malformed KV events for NVIDIA Dynamo
#13488 opened Nov 18, 2025 by PeaBrane Loading…
5 tasks done
@xiezhq-hermann
2
[Performance] Replace preprocess_video logic from GLM and Qwen-VL multimodal processor with transformer impl for speed up (up to 27% faster) and addressing OOM (up to 50x improvements) dependencies Pull requests that update a dependency file run-ci
#13487 opened Nov 18, 2025 by byjiang1996 Loading…
5 tasks done
@yhyang201
2
Fix global scaling factor loading hang quant LLM Quantization run-ci
#13484 opened Nov 18, 2025 by wenscarl Loading…
5 tasks
3
purge unnecessary env variable set in deterministic test run-ci
#13481 opened Nov 18, 2025 by zminglei Loading…
5 tasks
[Piecewise CUDA Graph] Support Triton Block W8A8 piecewise-cuda-graph run-ci
#13480 opened Nov 18, 2025 by b8zhong Loading…
2
[Spec v2] delay seq_lens sync and apply new memory manangment run-ci
#13478 opened Nov 18, 2025 by hnyls2002 Loading…
3
ProTip! Mix and match filters to narrow down what you’re looking for.