Shadowgraph
About
Sign in
← Explore by area

Cluster 452128

4 repos

Python · 2
C++ · 1
Rust · 1
inference ·12
moe ·12
diffusion-models ·7
local-llm ·7
diffusion-language-models ·7
self-hosted ·7
kimi-k3 ·5
cpu-inference ·5
io-uring ·5
cpp ·5

Related clusters

LLM Inference Optimization & Serving23Cluster 46212124Local LLM Inference Optimization19MLX framework for Apple Silicon ML22SIMD and vectorization libraries21Qwen LLM Model Variants34

ims-kdks/TIDE

TIDE: Efficient and Lossless MoE Diffusion LLM Inference with I/O-aware Expert Offload

Python

7

22 commits

Maknee/Kimi-K3.cpp

Run Kimi-K3 (2.8T MoE) from SSD with a tiny readable C++17 engine—native MXFP4, io_uring, and…

C++

5

4 commits

flashserve/Mosaic

MOSAIC: Unlocking Over 30× Context Length for Diffusion LLMs Inference via Global Memory Planning…

Python

5

1 commits

argonautlabsai/deltafin

ARGODRIVE Deltafin: Kimi K3 (2.8T MoE) streamed from SSDs on Apple Silicon — fork of…

Rust

84

41 commits