4 commits

Author	SHA1	Message	Date
Justine Tunney	e7eb0b3070	Make more ML improvements ... - Fix UX issues with llama.com - Do housekeeping on libm code - Add more vectorization to GGML - Get GGJT quantizer programs working well - Have the quantizer keep the output layer as f16c - Prefetching improves performance 15% if you use fewer threads	2023-05-16 08:07:23 -07:00
Justine Tunney	89d1fad7ee	Enable crash reports for radpajama executables	2023-05-13 21:16:03 -07:00
Justine Tunney	296ee3ec58	Make some other fixes to radpajama build config	2023-05-13 21:09:28 -07:00
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