MInference

AgentLLM Inferencellmai-appawesome-list

To speed up Long-context LLMs' inference, approximate and dynamic sparse calculate the attention, which reduces inference latency by up to 10x for pre-filling on an A100 while maintaining accuracy.

Directory Presence

Cross-referenced across 55 tracked directories

Directory	Status	First Seen	Last Confirmed	Link
A Awesome LLM Apps		3/13/2026	10/27/2026

Adoption Metrics & Statistics

#2808

Popularity Rank

1 / 55

Listed In

Emerging

Adoption Stage

5/22/2024

Created

1,198

GitHub Stars

Forks

Open Issues

3/9/2026

Last Commit

Recently added to the ecosystem

Health Score

49/100

Directory Presence5/20

Community22/30

Usage10/20

Development Activity12/30

Directory Adoption Over Time

Mar 13, 26: + Awesome LLM Apps

Security Analysis

Score: 100/100

0 dependency vulnerabilities found

AI Security Scan

Related Agents

TensorRT-LLM

NVIDIA Corporation

Nvidia Framework for LLM Inference

AgentLLM Inference

13K2 dirs

LMDeploy

A high-throughput and low-latency inference and serving framework for LLMs and VLs

AgentLLM Inference

7.7K2 dirs

Liger-Kernel

Efficient Triton Kernels for LLM Training.

AgentLLM Inference

6.2K2 dirs

SGLang

SGLang is a fast serving framework for large language models and vision language models.

AgentLLM Inference

25K1 dir