Daniel Hiltgen 39ca55a1ba Move quantization to new backend (#10363) ... * Move quantization logic to GGML via new backend This moves the model aware logic to Go code and calls GGMLs quantization code for model creation. * Remove "add model quantizations" This is no longer needed now that quantization is implemented in Go+GGML code directly.		2025-12-29 06:37:52 -06:00
..
llama-adapter.cpp	llama: update to commit 71e90e88 (#10192)	2025-12-29 06:37:39 -06:00
llama-adapter.h	llama: update to commit 71e90e88 (#10192)	2025-12-29 06:37:39 -06:00
llama-arch.cpp	Move quantization to new backend (#10363)	2025-12-29 06:37:52 -06:00
llama-arch.h	Move quantization to new backend (#10363)	2025-12-29 06:37:52 -06:00
llama-batch.cpp	next build (#8539)	2025-01-29 15:03:38 -08:00
llama-batch.h	llama: update to commit 71e90e88 (#10192)	2025-12-29 06:37:39 -06:00
llama-chat.cpp	llama: update to commit e1e8e099 (#10513)	2025-12-29 06:37:49 -06:00
llama-chat.h	llama: update to commit e1e8e099 (#10513)	2025-12-29 06:37:49 -06:00
llama-context.cpp	llama: update to commit e1e8e099 (#10513)	2025-12-29 06:37:49 -06:00
llama-context.h	llama: update to commit e1e8e099 (#10513)	2025-12-29 06:37:49 -06:00
llama-cparams.cpp	next build (#8539)	2025-01-29 15:03:38 -08:00
llama-cparams.h	llama: update to commit 71e90e88 (#10192)	2025-12-29 06:37:39 -06:00
llama-grammar.cpp	llama: remove model loading for grammar (#10096)	2025-12-29 06:37:41 -06:00
llama-grammar.h	llama: remove model loading for grammar (#10096)	2025-12-29 06:37:41 -06:00
llama-graph.cpp	llama: update to commit e1e8e099 (#10513)	2025-12-29 06:37:49 -06:00
llama-graph.h	llama: update to commit e1e8e099 (#10513)	2025-12-29 06:37:49 -06:00
llama-hparams.cpp	llama: update to commit 71e90e88 (#10192)	2025-12-29 06:37:39 -06:00
llama-hparams.h	llama: update to commit e1e8e099 (#10513)	2025-12-29 06:37:49 -06:00
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-io.cpp	llama: update to commit 71e90e88 (#10192)	2025-12-29 06:37:39 -06:00
llama-io.h	llama: update to commit 71e90e88 (#10192)	2025-12-29 06:37:39 -06:00
llama-kv-cache.cpp	llama: update to commit 2016f07b (#10352)	2025-12-29 06:37:42 -06:00
llama-kv-cache.h	llama: update to commit 71e90e88 (#10192)	2025-12-29 06:37:39 -06:00
llama-memory.cpp	llama: update to commit 71e90e88 (#10192)	2025-12-29 06:37:39 -06:00
llama-memory.h	llama: update to commit 71e90e88 (#10192)	2025-12-29 06:37:39 -06:00
llama-mmap.cpp	llama: update to commit 71e90e88 (#10192)	2025-12-29 06:37:39 -06:00
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 to commit 71e90e88 (#10192)	2025-12-29 06:37:39 -06:00
llama-model-loader.h	llama: update to commit 71e90e88 (#10192)	2025-12-29 06:37:39 -06:00
llama-model.cpp	Move quantization to new backend (#10363)	2025-12-29 06:37:52 -06:00
llama-model.h	llama: update to commit e1e8e099 (#10513)	2025-12-29 06:37:49 -06:00
llama-quant.cpp	Move quantization to new backend (#10363)	2025-12-29 06:37:52 -06:00
llama-quant.h	next build (#8539)	2025-01-29 15:03:38 -08:00
llama-sampling.cpp	llama: update to commit e1e8e099 (#10513)	2025-12-29 06:37:49 -06:00
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: update to commit e1e8e099 (#10513)	2025-12-29 06:37:49 -06:00
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 to commit 71e90e88 (#10192)	2025-12-29 06:37:39 -06:00
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 to commit 71e90e88 (#10192)	2025-12-29 06:37:39 -06:00
unicode.h	next build (#8539)	2025-01-29 15:03:38 -08:00