Skip to content

Pull requests: sgl-project/sglang

New pull request New
583 Open 5,763 Closed
583 Open 5,763 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

vlm: resume batching reqs in Vits to speedup
#9529 opened Aug 23, 2025 by mickqian • Draft
4 tasks
chore: include a minimal image for vlms when warming-up
#9528 opened Aug 23, 2025 by mickqian Loading…
4 tasks
7
Support modelopt llama4 nvfp4 workflow and fix issues
#9526 opened Aug 23, 2025 by Edwardf0t1 Loading…
1 of 4 tasks
tool-call(dsv3): Improve deepseek-v3 chat template and tool_choice = required
#9525 opened Aug 23, 2025 by CatherineSue Loading…
4 tasks
3
[router] address worker load tracking consistency wip bug Something isn't working router
#9523 opened Aug 22, 2025 by slin1237 Loading…
1 of 4 tasks
4
gb200: update dockerfile to latest kernel
#9522 opened Aug 22, 2025 by ishandhanani Loading…
3
fix: benchmark random sample
#9518 opened Aug 22, 2025 by xww9 Loading…
5
fix: benchmark chunks index out of range
#9517 opened Aug 22, 2025 by xww9 Loading…
3
[bugfix] failed to find greenctx related symbols when CUDA_VERSION < 12040
#9512 opened Aug 22, 2025 by cleanerleon Loading…
4 tasks
4
Support target verify with trtllm mla kernel in eagle3 speculative decoding high priority
#9509 opened Aug 22, 2025 by AHEADer Loading…
1 of 4 tasks
@yyihuang @Qiaolin-Yu
5
[Bugfix]fix error response in pd_router
#9505 opened Aug 22, 2025 by Bruce-x-1997 Loading…
4 tasks
6
[bugfix] support safe_dispatch env to use safe branch in pd_router
#9502 opened Aug 22, 2025 by Bruce-x-1997 Loading…
4 tasks
3
Fix 'KeyError' for per_token expert distribution recorder
#9501 opened Aug 22, 2025 by vipwangerxiao Loading…
1 of 4 tasks
4
Fix GLM45 tool call multi-turn bug
#9500 opened Aug 22, 2025 by byjiang1996 Loading…
4 tasks done
1
@CatherineSue @JustinTong0323
4
Return expert routing info to support MoE routing replay
#9499 opened Aug 22, 2025 by KawaiiNotHawaii Loading…
4 tasks
@fzyzcjy
8
[router] revert kube & kubeapi ver in sgl-router cargo.toml bug Something isn't working dependencies Pull requests that update a dependency file router
#9498 opened Aug 22, 2025 by Bruce-x-1997 Loading…
4 tasks
@CatherineSue @key4ng @slin1237
4
Feature: Support MOSS-TTSD model with its multi-channel token i/o and delay-pattern sampling
#9496 opened Aug 22, 2025 by CloudRipple Loading…
1 of 4 tasks
1
support cuda 13.0 and trtllm kernel by Aug 21 2025
#9495 opened Aug 22, 2025 by rainj-me • Draft
4 of 5 tasks
enable xpu ci
#9493 opened Aug 22, 2025 by DiweiSun Loading…
4 tasks
1
Optimize fused_moe_kernel with Split-K
#9486 opened Aug 22, 2025 by yuan-luo Loading…
4 tasks
8
Partially unify triton per token group quant kernels
#9485 opened Aug 22, 2025 by fzyzcjy Loading…
4 tasks
8
[bug] Remove double-formatted whitespace lines
#9479 opened Aug 22, 2025 by vincentzed Loading…
1 of 4 tasks
3
Tiny make device_loading_context more static
#9478 opened Aug 22, 2025 by fzyzcjy Loading…
4 tasks
4
Optimize moe_sum_reduce_kernel
#9477 opened Aug 22, 2025 by yuan-luo Loading…
4 tasks
7
[Benchmark] Add mLLM benchmark + CI
#9476 opened Aug 22, 2025 by vincentzed Loading…
4 tasks
1
ProTip! What’s not been updated in a month: updated:<2025-07-23.