# moe

このトピックのトレンドリポジトリ（3件）

vllm-project/vllm

vllm-project/vllmOtherPython

94.7k2回登場

A high-throughput and memory-efficient inference and serving engine for LLMs

amdblackwellcudadeepseekdeepseek-v3gptgpt-ossinferencekimillamallmllm-servingmodel-servingmoeopenaipytorchqwenqwen3tputransformer

FlashML-org/FreeToken

FlashML-org/FreeTokenOtherPython

15.9k2回登場

FreeToken brings datacenter-scale model serving to your desktop. Run massive models locally, fast and efficiently.

deepseek-v4edgeglminferenceminimaxmoeqwentransformer

FareedKhan-dev/kimi-k3-in-c

FareedKhan-dev/kimi-k3-in-cOtherC

A 2.78-trillion-parameter Kimi K3 running inference on a single CPU in 8.24 GB of RAM. Portable C99: no BLAS, no framework, no GPU.

avx2c99cpu-inferencedeep-learningfrom-scratchinference-enginekimi-k3linear-attentionllmllm-inferencemachine-learningmemory-efficientmixture-of-expertsmoemxfp4quantizationsimdsystems-programmingtransformerzero-dependencies