8000 Pull requests · sgl-project/sglang · GitHub
[go: up one dir, main page]
Skip to content

Pull requests: sgl-project/sglang

New pull request New
312 Open 3,664 Closed
312 Open 3,664 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
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Pull requests list

Speed up when having padding tokens in DeepEP
#6175 opened May 10, 2025 by fzyzcjy Loading…
6 tasks
[fix]: Disable ASCII escaping for Chinese characters to prevent redundant backslashes in tool_call outputs during streaming responses. #6156
#6174 opened May 10, 2025 by tdeng521 Loading…
6 tasks
Fix OpenAI Client error with single request via batch api
#6170 opened May 10, 2025 by ravi03071991 Loading…
6 tasks
5
fix: handle None multimodal_inputs during merging and filtering batches in disaggregation decode mode
#6169 opened May 10, 2025 by GaoYusong Loading…
1 of 6 tasks
Benchmark scripts for attn_backend
#6168 opened May 10, 2025 by byjiang1996 • Draft
1 of 6 tasks
[Docs] [QUANT] Install vLLM for specific quant methods
#6167 opened May 10, 2025 by JiangJiaWei1103 Loading…
2 of 6 tasks
Cache Aware Router improvement
#6164 opened May 9, 2025 by YouNeedCryDear Loading…
4 of 6 tasks
@ByronHsu @hnyls2002
[Fix] fix assert error in disaggregatin decoder
#6155 opened May 9, 2025 by zeroorhero Loading…
1 of 6 tasks
[doc] add a note for --n-share-experts-fusion args
#6154 opened May 9, 2025 by BBuf Loading…
6 tasks
add profile for bench one batch server
#6153 opened May 9, 2025 by xutizhou Loading…
6 tasks
3
[Feat] optimize Qwen3 on H20 by hybrid Attention Backend
#6151 opened May 9, 2025 by TianQiLin666666 Loading…
6 tasks
[Bug Fixed] fixed the triton kernel bug of assign_draft_cache_locs for page_size > 1 in eagle mode
#6150 opened May 9, 2025 by DavidChan0519 Loading…
Reduce MoE memory usage
#6147 opened May 9, 2025 by fzyzcjy Loading…
6 tasks
1
[Docs]Delete duplicate content
#6146 opened May 9, 2025 by Ximingwang-09 Loading…
6 tasks
1
[WIP] Apply optimizations in DeepSeek forward_absorb to forward_normal
#6144 opened May 9, 2025 by Fridge003 • Draft
3 of 10 tasks
Add intel_amx backend for Radix Attention
#6143 opened May 9, 2025 by yanbing-j • Draft
6 tasks
2
Enable native ModelOpt quantization support (1/3)
#6142 opened May 9, 2025 by Edwardf0t1 Loading…
1 of 6 tasks
doc: update developer guide regarding mllms
#6138 opened May 9, 2025 by mickqian Loading…
6 tasks
2
Implement return_hidden_states for the OpenAI API
#6137 opened May 9, 2025 by kyle-pena-kuzco Loading…
2 of 6 tasks
1
Support precomputed multimodal features for qwen-vl models.
#6136 opened May 9, 2025 by ysulsky Loading…
4 of 6 tasks
Support multi-round conversations in bench_serving
#6135 opened May 9, 2025 by fzyzcjy Loading…
6 tasks
Tiny refactor bench_serving to improve extensibility
#6134 opened May 9, 2025 by fzyzcjy Loading…
6 tasks
1
[ROCm][CI]: add VLM PR CI for parity with NVIDIA visIon-LM
#6130 opened May 8, 2025 by OrenLeung Loading…
4 of 6 tasks
@JustinTong0323
1
Fix XGrammar bug in PD.
#6127 opened May 8, 2025 by Zhou-sx Loading…
1 of 6 tasks
Example for reasoning parser.
#6126 opened May 8, 2025 by simveit Loading…
ProTip! Updated in the last three days: updated:>2025-05-07.
0