Product
Help
Pricing
About
Jobs
Log in
Get started
Keyword
Add to collection
SGLang
Description:
SGLang is an open-source framework for serving and performing inference with large language models.
Primary topic:
Parallel Computing and Optimization Techniques (35%)
Related topics:
Parallel Computing and Optimization Techniques (35%),
Natural Language Processing Techniques (15%),
Topic Modeling (7%)
Wikidata ID:
wiki/Q139761223
OpenAlex ID:
keywords/sglang
LMCache: An Efficient KV Cache Layer for Enterprise-Scale LLM Inference
2025
·
Liu, Yuhan
, Cheng, Yihua
, et al.
·
arXiv (Cornell University)
·
233
PDF
Defeating Nondeterminism in LLM Inference
2025
·
Thinking Machines Lab
, Horace He
, et al.
·
191
Astra: A Multi-Agent System for GPU Kernel Performance Optimization
2025
·
Wei, Anjiang
, Sun, Tianran
, et al.
·
arXiv (Cornell University)
·
90
PDF
TorchAO: PyTorch-Native Training-to-Serving Model Optimization
2025
·
Or, Andrew
, Jain, Apurva
, et al.
·
arXiv (Cornell University)
·
45
PDF
FlashInfer-Bench: Building the Virtuous Cycle for AI-driven LLM Systems
2026
·
Xing, Shanli
, Zhai, Yiyan
, et al.
·
arXiv (Cornell University)
·
37
PDF
SpecForge: A Flexible and Efficient Open-Source Training Framework for Speculative Decoding
2026
·
Li, Shenggui
, Wang, Chao
, et al.
·
arXiv (Cornell University)
·
23
PDF
AIConfigurator: Lightning-Fast Configuration Optimization for Multi-Framework LLM Serving
2026
·
Xu, Tianhao
, Liu, Yiming
, et al.
·
arXiv (Cornell University)
·
23
PDF
Semantic Parallelism: Redefining Efficient MoE Inference via Model-Data Co-Scheduling
2025
·
Li, Yan
, Zhang, Zhenyu
, et al.
·
arXiv (Cornell University)
·
21
PDF
UCCL-EP: Portable Expert-Parallel Communication
2025
·
Mao, Ziming
, Zhang, Yihan
, et al.
·
arXiv (Cornell University)
·
20
PDF
A Survey of LLM Inference Systems
2025
·
Pan, James
, Li, Guoliang
·
arXiv (Cornell University)
·
20
PDF
InfiniteHiP: Extending Language Model Context Up to 3 Million Tokens on a Single GPU
2025
·
Lee, Heejun
, Park, Geon
, et al.
·
arXiv (Cornell University)
·
17
PDF
FP8-RL: A Practical and Stable Low-Precision Stack for LLM Reinforcement Learning
2026
·
Qiu, Zhaopeng
, Yu, Shuang
, et al.
·
arXiv (Cornell University)
·
16
PDF
Native Parallel Reasoner: Reasoning in Parallelism via Self-Distilled Reinforcement Learning
2025
·
Wu, Tong
, Liu, Yang
, et al.
·
arXiv (Cornell University)
·
15
PDF
The Silent Hyperparameter: Quantifying the Impact of Inference Backends on LLM Reproducibility
2026
·
Pape, David
, Evertz, Jonathan
, et al.
·
arXiv (Cornell University)
·
13
PDF
Fast-dVLM: Efficient Block-Diffusion VLM via Direct Conversion from Autoregressive VLM
2026
·
Wu, Chengyue
, Lan, Shiyi
, et al.
·
arXiv (Cornell University)
·
13
PDF
Kernel-Smith: A Unified Recipe for Evolutionary Kernel Optimization
2026
·
Du, He
, Ge, Qiming
, et al.
·
arXiv (Cornell University)
·
13
PDF
ECHO: Elastic Speculative Decoding with Sparse Gating for High-Concurrency Scenarios
2026
·
Hu, Xinyi
, Shen, Yuhao
, et al.
·
arXiv (Cornell University)
·
13
PDF
KDFlow: A User-Friendly and Efficient Knowledge Distillation Framework for Large Language Models
2026
·
Songming Zhang
, Xue Zhang
, et al.
·
Conference on Empirical Methods in Natural Language Processing: System Demonstrations (EMNLP)
·
11
PDF
VLCache: Computing 2% Vision Tokens and Reusing 98% for Vision-Language Inference
2025
·
Qin, Shengling
, Yu, Hao
, et al.
·
arXiv (Cornell University)
·
11
PDF
ISO-Bench: Can Coding Agents Optimize Real-World Inference Workloads?
2026
·
Nangia, Ayush
, Mishra, Shikhar
, et al.
·
arXiv (Cornell University)
·
10
PDF
HiSparse: Scaling Sparse-Attention Decoding with Hierarchical KV Cache Management
2026
·
Xie, Zhiqiang
, Huang, Zhangheng
, et al.
·
arXiv (Cornell University)
·
8
PDF
Revati: Transparent GPU-Free Time-Warp Emulation for LLM Serving
2026
·
Agrawal, Amey
, Yadav, Mayank
, et al.
·
arXiv (Cornell University)
·
8
PDF
Ragged Paged Attention: A High-Performance and Flexible LLM Inference Kernel for TPU
2026
·
Jiang, Jevin
, Chen, Ying
, et al.
·
arXiv (Cornell University)
·
7
PDF
Making Every Verified Token Count: Adaptive Verification for MoE Speculative Decoding
2026
·
Lehan Pan
, Ziyang Tao
, et al.
·
Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)
·
7
PDF
Miles v0.1: Production-Level Post-Training
2026
·
RadixArk
, :
, et al.
·
arXiv (Cornell University)
·
6
PDF
Show more works
View as search
Works count:
152
Citation count:
1,017
Year
Topic
Type