Skip to content

Pull requests: sgl-project/sglang

New pull request New
67 Open 2,169 Closed
67 Open 2,169 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

Update Intel XPU install instruction
#3390 opened Feb 8, 2025 by airMeng Loading…
2 of 5 tasks
Add H20 fp8 w8a8 gemm config
#3386 opened Feb 8, 2025 by sleepcoo Loading…
2
[BUG] fix moe benchmark when bs*seq is small
#3382 opened Feb 7, 2025 by yiakwy-xpu-ml-framework-team Loading…
3 of 5 tasks
Started with document.
#3381 opened Feb 7, 2025 by simveit • Draft
Docs: Add Slurm Example on Multi-Nodes amd documentation Improvements or additions to documentation
#3379 opened Feb 7, 2025 by zhaochenyang20 Loading…
2 of 5 tasks
@zhaochenyang20
12
Better support of tp checkpoint loading
#3367 opened Feb 7, 2025 by yinghai Loading…
3 tasks done
1
[Feat] return hidden states
#3364 opened Feb 7, 2025 by Jackmin801 Loading…
3 of 5 tasks
8
Add support for OpenAI API o1 model
#3363 opened Feb 7, 2025 by ChuyueSun Loading…
2 of 5 tasks
fix(mig): fallback gpu_memory_total value
#3353 opened Feb 6, 2025 by tomheno Loading…
1
feature: Intern vl 2.5
#3351 opened Feb 6, 2025 by mickqian • Draft
5 tasks
1
Tiny fix Olmo2
#3348 opened Feb 6, 2025 by fzyzcjy Loading…
3 of 5 tasks
Update fused_moe's benchmark
#3346 opened Feb 6, 2025 by WhatGhost Loading…
1 of 5 tasks
6
FEA compat with ipv6 amd good first issue Good for newcomers help wanted Extra attention is needed
#3301 opened Feb 4, 2025 by lxww302 Loading…
4 tasks done
1
@shuaills
2
[Feature] Support llguidance for constrained decoding
#3298 opened Feb 4, 2025 by JC1DA Loading…
2 of 3 tasks
add date_string to the chat template
#3297 opened Feb 4, 2025 by cctry Loading…
4 tasks
6
support blockwise fp8 matmul kernel
#3267 opened Feb 3, 2025 by yizhang2077 Loading…
4 tasks
2
Update metrics documentation
#3264 opened Feb 2, 2025 by binarycrayon Loading…
2 of 4 tasks
7
Draft of updated doc for sampling params.
#3260 opened Feb 2, 2025 by simveit • Draft
feat: Support Qwen 2.5 vl
#3258 opened Feb 2, 2025 by mickqian Loading…
3 of 4 tasks
1
[Docs] add quantization docs
#3253 opened Feb 1, 2025 by yinfan98 Loading…
4 tasks
8
[ROCm] Enable Fused MLA Triton kernel for DeepSeekV3
#3237 opened Jan 31, 2025 by lcskrishna • Draft
@HaiShaw
docs(references/deepseek): current section links
#3225 opened Jan 31, 2025 by guspan-tanadi Loading…
4 tasks
Add support for nvidia modelopt fp8 kv cache high priority
#3223 opened Jan 30, 2025 by Edwardf0t1 Loading…
1 of 4 tasks
@zhyncs
Online serving benchmarks of real datasets for hierarchical KV caching
#3211 opened Jan 30, 2025 by PanJason Loading…
5 tasks
@xiezhq-hermann
Specify torch==2.5.1 in pyproject.toml
#3210 opened Jan 30, 2025 by merrymercy Loading…
ProTip! Type g i on any issue or pull request to go back to the issue listing page.