2 commits

Author	SHA1	Message	Date
Justine Tunney	282dd8e7b7	Get radpajama to build ... make -j8 o//third_party/radpajama/radpajama.com make -j8 o//third_party/radpajama/radpajama-chat.com This change gets the radpajama.mk config working. This package depends on THIRD_PARTY_GGML but it's configured to call ggjt_v1(), so that the library will provide the old quantizers. The ggml_quantize_chunk() API will now dispatch to older quantizers based on the configured version.	2023-05-13 20:44:36 -07:00
Justine Tunney	5a4cf9560f	Add support for new GGJT v2 quantizers ... This change makes quantized models (e.g. q4_0) go 10% faster on Macs however doesn't offer much improvement for Intel PC hardware. This change syncs llama.cpp 699b1ad7fe6f7b9e41d3cb41e61a8cc3ea5fc6b5 which recently made a breaking change to nearly all its file formats without any migration. Since that'll break hundreds upon hundreds of models on websites like HuggingFace llama.com will support both file formats because llama.com will never ever break the GGJT file format	2023-05-13 08:08:32 -07:00