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++
0.2.0bin/baby-llamabin/batchedbin/batched-benchbin/beam-searchbin/benchmarkbin/convert-llama2c-to-ggmlbin/convert-lora-to-ggml.pybin/convert.pybin/embeddingbin/export-lorabin/finetunebin/ggufbin/gguf-splitbin/gritlmbin/imatrixbin/infillbin/llamabin/llama-benchbin/llama-serverbin/llava-clibin/lookaheadbin/lookupbin/parallelbin/passkeybin/perplexitybin/quantizebin/quantize-statsbin/save-load-statebin/simplebin/speculativebin/test-autoreleasebin/test-backend-opsbin/test-chat-templatebin/test-grad0bin/test-grammar-parserbin/test-llama-grammarbin/test-model-load-cancelbin/test-quantize-fnsbin/test-quantize-perfbin/test-ropebin/test-samplingbin/test-tokenizer-0-falconbin/test-tokenizer-0-llamabin/test-tokenizer-1-bpebin/test-tokenizer-1-llamabin/tokenizebin/train-text-from-scratchaarch64-darwinaarch64-freebsdaarch64-linuxaarch64-netbsdarc-linuxarmv5tel-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-linuxsh4-linuxx86_64-cygwinx86_64-freebsdx86_64-linuxx86_64-netbsdx86_64-openbsdx86_64-redoxx86_64-solaris