9 Commits

Author	SHA1	Message	Date
Radoslav Gerganov	62042b741f	ggml : remove ggml_graph_import and ggml_graph_export declarations (#1247) ... The implementation is already deleted with commit 9d0762e. closes: #1235	2025-05-30 09:11:09 +03:00
Georgi Gerganov	5378ea0d3c	ggml : reorganize source code + improve CMake (#865) ... * scripts : update sync [no ci] * ggml : move headers one up [no ci] * files : reorganize + update CMake ggml-ci * cmake : build normal ggml library ggml-ci * cmake : link math library to test + remove ci for code cov ggml-ci * files : move public headers to include ggml-ci	2024-06-26 19:33:53 +03:00
Georgi Gerganov	39060c7b41	examples : more CUDA leftovers (#0)	2024-03-27 13:20:00 +02:00
Georgi Gerganov	af32597662	examples : fix CUBLAS leftovers (#0) ... ggml-ci	2024-03-27 13:20:00 +02:00
Timothy Cronin	f841cd014d	ggml : remove ggml_cpy_inplace and ggml_cont_inplace (#693)	2024-01-11 09:27:48 +02:00
Olivier Chafik	17214838d4	python: regenerate bindings + cosmetic cleanups	2023-08-22 10:52:03 +01:00
ochafik	548aa504e0	Added some tests to python example + fixed numpy on scalar tensors	2023-08-14 02:17:29 +01:00
ochafik	6d33164233	Simple python stub (*.pyi) generator for cffi	2023-08-13 20:05:13 +01:00
ochafik	53a0003018	Add python example w/ cffi-generated bindings ... Add python example w/ cffi-generated bindings Features: - Seamless copies between tensors (ggml & numpy alike) with automatic (de/re)quantization - Access to full C API (incl. CUDA, MPI, OpenCL, Metal, alloc... and any local API changes) - Trivial regeneration with `python regenerate.py` (uses llama.cpp headers by default, README.md for options)	2023-08-13 20:05:13 +01:00