Skip to content

Pull requests: sgl-project/sglang

New pull request New
382 Open 4,424 Closed
382 Open 4,424 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

[WIP]Add gemma3n
#7344 opened Jun 19, 2025 by JustinTong0323 • Draft
6 tasks
10
[Docker] optimize dockerfile remove deepep and blackwell merge it to…
#7343 opened Jun 19, 2025 by whybeyoung Loading…
8
[BugFix] Fix AssertionError: res=<Response [502]>, res.text=''
#7341 opened Jun 19, 2025 by gty111 Loading…
1 of 6 tasks
2
fix the abnormal GPU memory occupation of multimodal model continued to increase until OOM
#7340 opened Jun 19, 2025 by huangtingwei9988 Loading…
6 tasks
7
[NVIDIA] Add Jetson Orin/Thor and Spark Codegen
#7337 opened Jun 19, 2025 by johnnynunez Loading…
2
[NVIDIA] Jetson Compatibility
#7336 opened Jun 19, 2025 by johnnynunez Loading…
3
[OAI Server Refactor] [ChatCompletions & Completions] Support Return Hidden State
#7329 opened Jun 18, 2025 by key4ng Loading…
4 of 8 tasks
@CatherineSue
6
[Fix] fix decode OOM due to wrong estimation when ignore_eos
#7328 opened Jun 18, 2025 by DarkSharpness Loading…
1 of 6 tasks
@xiezhq-hermann
4
Add FlashInfer NVFP4 MoE for Blackwell with MOE-EP support high priority
#7327 opened Jun 18, 2025 by trevor-m Loading…
6 tasks
@BBuf @pyc96
12
Purge VerlEngine
#7326 opened Jun 18, 2025 by MrAta Loading…
1 of 5 tasks
3
[NVIDIA] Fix Jetson Build
#7323 opened Jun 18, 2025 by johnnynunez Loading…
3
Feat/refactor embedding server
#7322 opened Jun 18, 2025 by woodx9 Loading…
1 of 6 tasks
@CatherineSue
5
Fix GuidanceGrammar bitmask
#7321 opened Jun 18, 2025 by YorkSu Loading…
1 of 6 tasks
1
3
[doc] update lws doc for pd
#7318 opened Jun 18, 2025 by whybeyoung Loading…
10
Add the missing logic to update existing PD monitoring metrics
#7317 opened Jun 18, 2025 by SCDESPERTATE • Draft
2
[NVIDIA] Avoid OOM issues aarch64 wheels
#7316 opened Jun 18, 2025 by johnnynunez Loading…
8
support Qwen3ForSequenceClassification
#7314 opened Jun 18, 2025 by bzantium Loading…
3 of 6 tasks
3
Kernels for efficient KV cache IO
#7313 opened Jun 18, 2025 by xiezhq-hermann Loading…
1 of 6 tasks
@merrymercy @xiezhq-hermann
@ByronHsu @zhyncs
7
Add get_hidden_dim to qwen3.py for correct lora
#7312 opened Jun 18, 2025 by logachevpa Loading…
7
Let EP prefill support new DeepGEMM high priority
#7310 opened Jun 18, 2025 by fzyzcjy Loading…
6 tasks
@Alcanderian @ch-wan
4
Let ep_scatter support arbitrary strides / ue8m0 format high priority
#7309 opened Jun 18, 2025 by fzyzcjy Loading…
6 tasks
@Alcanderian
4
Tiny add logs for expert location updater
#7308 opened Jun 18, 2025 by fzyzcjy Loading…
6 tasks
3
[Refactor] Clean up radix cache related API
#7303 opened Jun 18, 2025 by DarkSharpness Loading…
1 of 6 tasks
@xiezhq-hermann
14
Support FP4 quantized models on AMD CDNA2/CDNA3 GPUs
#7302 opened Jun 18, 2025 by haohui Loading…
6 tasks done
7
[wip] use trt-llm(flashinfer) cutlass moe in b200
#7296 opened Jun 18, 2025 by BBuf • Draft
6 tasks
6
ProTip! Find all pull requests that aren't related to any open issues with -linked:issue.