llama.cpp

mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-09-03 11:35:37 +02:00

Files

T

DAN™ d62b532c52 Use model->gguf_kv for loading the template instead of using the C API. (#10868 )

* Bump model_template to 16384 bytes to support larger chat templates.

* Use `model->gguf_kv` for efficiency.

2024-12-17 23:24:22 +01:00

CMakeLists.txt

2024-12-12 19:02:49 +01:00

llama-grammar.cpp

2024-09-07 15:16:19 +03:00

llama-grammar.h

2024-09-07 15:16:19 +03:00

llama-impl.h

2024-09-24 10:15:35 +03:00

llama-sampling.cpp

2024-12-16 12:31:14 +02:00

llama-sampling.h

2024-10-25 19:07:34 +03:00

llama-vocab.cpp

2024-12-16 12:31:45 +02:00

llama-vocab.h

2024-10-25 19:07:34 +03:00

llama.cpp

2024-12-17 23:24:22 +01:00

unicode-data.cpp

2024-10-08 13:27:04 +02:00

unicode-data.h

2024-10-02 15:49:55 +02:00

unicode.cpp

2024-12-16 12:31:45 +02:00

unicode.h

2024-12-16 12:31:45 +02:00