Mirage Persistent Kernel: Compiling LLMs into a MegaKernel
Appears on
Quick read
Latest capture 2026-09-07 10:55
103 paths
Agent instructions and tool configuration found in this repository.
Claude Code 103
79 more paths detected.
1 observed capture since 2026-09-07. Observed captures are shown by default.
Stars from first capture 0
Observed captures only
All tracked data
Observed snapshots
Observed snapshots
Nearest indexed repositories by embedding similarity.
Ongoing research training transformer models at scale
Universal LLM Deployment Engine with ML Compilation
A Flexible Framework for Experiencing Heterogeneous LLM Inference/Fine-tune Optimizations
LMCache: Supercharge Your LLM with the Fastest KV Cache Layer
LMDeploy is a toolkit for compressing, deploying, and serving LLMs.
OpenMMLab Foundational Library for Training Deep Learning Models
