ollama/llama/llama.cpp/src
Bruce MacDonald 6bd0a983cd model: support for mistral-small in the ollama runner
Mistral is a popular research lab making open source models. This updates
the forward pass of llama architecture models to support both llama models
and mistral models by accounting for additional metadata present in mistral
models, and finding the correct dimensions for the output projection.
2025-04-03 16:57:36 -07:00
..
llama-adapter.cpp llama: update llama.cpp vendor code to commit d7cfe1ff (#9356) 2025-02-26 20:34:44 -08:00
llama-adapter.h llama: update llama.cpp vendor code to commit d7cfe1ff (#9356) 2025-02-26 20:34:44 -08:00
llama-arch.cpp model: support for mistral-small in the ollama runner 2025-04-03 16:57:36 -07:00
llama-arch.h model: support for mistral-small in the ollama runner 2025-04-03 16:57:36 -07:00
llama-batch.cpp next build (#8539) 2025-01-29 15:03:38 -08:00
llama-batch.h next build (#8539) 2025-01-29 15:03:38 -08:00
llama-chat.cpp llama: update llama.cpp vendor code to commit d7cfe1ff (#9356) 2025-02-26 20:34:44 -08:00
llama-chat.h llama: update llama.cpp vendor code to commit d7cfe1ff (#9356) 2025-02-26 20:34:44 -08:00
llama-context.cpp llama: update llama.cpp vendor code to commit d7cfe1ff (#9356) 2025-02-26 20:34:44 -08:00
llama-context.h llama: update llama.cpp vendor code to commit d7cfe1ff (#9356) 2025-02-26 20:34:44 -08:00
llama-cparams.cpp next build (#8539) 2025-01-29 15:03:38 -08:00
llama-cparams.h next build (#8539) 2025-01-29 15:03:38 -08:00
llama-grammar.cpp llama: update llama.cpp vendor code to commit d7cfe1ff (#9356) 2025-02-26 20:34:44 -08:00
llama-grammar.h llama: update llama.cpp vendor code to commit d7cfe1ff (#9356) 2025-02-26 20:34:44 -08:00
llama-hparams.cpp llama: update llama.cpp vendor code to commit d7cfe1ff (#9356) 2025-02-26 20:34:44 -08:00
llama-hparams.h llama: update llama.cpp vendor code to commit d7cfe1ff (#9356) 2025-02-26 20:34:44 -08:00
llama-impl.cpp llama: update llama.cpp vendor code to commit d7cfe1ff (#9356) 2025-02-26 20:34:44 -08:00
llama-impl.h llama: update llama.cpp vendor code to commit d7cfe1ff (#9356) 2025-02-26 20:34:44 -08:00
llama-kv-cache.cpp llama: update llama.cpp vendor code to commit d7cfe1ff (#9356) 2025-02-26 20:34:44 -08:00
llama-kv-cache.h llama: update llama.cpp vendor code to commit d7cfe1ff (#9356) 2025-02-26 20:34:44 -08:00
llama-mmap.cpp llama: update llama.cpp vendor code to commit d7cfe1ff (#9356) 2025-02-26 20:34:44 -08:00
llama-mmap.h llama: update llama.cpp vendor code to commit d7cfe1ff (#9356) 2025-02-26 20:34:44 -08:00
llama-model-loader.cpp llama: update llama.cpp vendor code to commit d7cfe1ff (#9356) 2025-02-26 20:34:44 -08:00
llama-model-loader.h llama: update llama.cpp vendor code to commit d7cfe1ff (#9356) 2025-02-26 20:34:44 -08:00
llama-model.cpp model: support for mistral-small in the ollama runner 2025-04-03 16:57:36 -07:00
llama-model.h llama: update llama.cpp vendor code to commit d7cfe1ff (#9356) 2025-02-26 20:34:44 -08:00
llama-quant.cpp model: support for mistral-small in the ollama runner 2025-04-03 16:57:36 -07:00
llama-quant.h next build (#8539) 2025-01-29 15:03:38 -08:00
llama-sampling.cpp llama: update llama.cpp vendor code to commit d7cfe1ff (#9356) 2025-02-26 20:34:44 -08:00
llama-sampling.h llama: update llama.cpp vendor code to commit d7cfe1ff (#9356) 2025-02-26 20:34:44 -08:00
llama-vocab.cpp llama: fix kv loading on snowflake-arctic-embed models (#9536) 2025-03-07 09:25:34 -08:00
llama-vocab.h llama: update llama.cpp vendor code to commit d7cfe1ff (#9356) 2025-02-26 20:34:44 -08:00
llama.cpp llama: update llama.cpp vendor code to commit d7cfe1ff (#9356) 2025-02-26 20:34:44 -08:00
llama.go Revert "cgo: use O3" 2025-01-31 10:25:39 -08:00
unicode-data.cpp next build (#8539) 2025-01-29 15:03:38 -08:00
unicode-data.h next build (#8539) 2025-01-29 15:03:38 -08:00
unicode.cpp llama: update llama.cpp vendor code to commit d7cfe1ff (#9356) 2025-02-26 20:34:44 -08:00
unicode.h next build (#8539) 2025-01-29 15:03:38 -08:00