Description
Inference of Meta's LLaMA model (and others) in pure C/C++
Inference of Meta's LLaMA model (and others) in pure C/C++
6442bin/llamabin/speculativebin/convert.pybin/test-backend-opsbin/test-model-load-cancelbin/save-load-statebin/batchedbin/test-grammar-parserbin/test-quantize-perfbin/test-ropebin/quantize-statsbin/imatrixbin/test-tokenizer-1-bpebin/parallelbin/infillbin/train-text-from-scratchbin/gritlmbin/beam-searchbin/lookaheadbin/embeddingbin/lookupbin/perplexitybin/tokenizebin/benchmarkbin/test-autoreleasebin/test-quantize-fnsbin/convert-lora-to-ggml.pybin/passkeybin/test-chat-templatebin/gguf-splitbin/llava-clibin/simplebin/finetunebin/test-tokenizer-1-llamabin/test-grad0bin/test-tokenizer-0-falconbin/batched-benchbin/test-samplingbin/convert-llama2c-to-ggmlbin/test-tokenizer-0-llamabin/baby-llamabin/llama-serverbin/export-lorabin/test-llama-grammarbin/quantizebin/llama-benchbin/ggufaarch64-darwinaarch64-freebsdaarch64-linuxaarch64-netbsdarmv5tel-linuxarmv6l-linuxarmv6l-netbsdarmv7a-linuxarmv7a-netbsdarmv7l-linuxarmv7l-netbsdi686-cygwini686-freebsdi686-linuxi686-netbsdi686-openbsdloongarch64-linuxm68k-linuxm68k-netbsdmicroblaze-linuxmicroblazeel-linuxmips-linuxmips64-linuxmips64el-linuxmipsel-linuxmipsel-netbsdpowerpc-linuxpowerpc-netbsdpowerpc64-linuxpowerpc64le-linuxriscv32-linuxriscv32-netbsdriscv64-linuxriscv64-netbsds390-linuxs390x-linuxx86_64-cygwinx86_64-darwinx86_64-freebsdx86_64-linuxx86_64-netbsdx86_64-openbsdx86_64-redoxx86_64-solaris