The Local LLM Index / Local UIs & Apps / #221
modelscope/dash-infer
by modelscope · Local UIs & Apps · updated 1y ago
DashInfer is a native LLM inference engine aiming to deliver industry-leading performance atop various hardware architectures, including CUDA, x86 and ARMv9.
27
momentum
272
stars
29
forks
#221
rank
cpucudaguided-decodingllmllm-inferencenative-engine
View on GitHub →