ik_llama.cpp.git - Unnamed repository; edit this file 'description' to name the repository.

Age	Commit message (Expand)	Author
2023-09-07	fix some warnings from gcc and clang-tidy (#3038)	Cebtenzzre
2023-09-07	metal : fix kernel_norm (fixes Falcon on Metal) (#3057)	Georgi Gerganov
2023-09-05	examples : replace fprintf to stdout with printf (#3017)	Cebtenzzre
2023-09-05	speculative : add grammar support (#2991)	Georgi Gerganov
2023-09-04	build : on Mac OS enable Metal by default (#2901)	Georgi Gerganov
2023-09-03	speculative : PoC for speeding-up inference via speculative sampling (#2926)	Georgi Gerganov
2023-09-03	perplexity : fix ETA by warming up the model with an empty run	Georgi Gerganov
2023-09-01	build : fix most gcc and clang warnings (#2861)	Cebtenzzre
2023-08-30	main : log file (#2748)	staviq
2023-08-28	train : mem usage and other improvements (#2439)	xaedes
2023-08-28	YAML result logging + preset script (#2657)	Johannes Gäßler
2023-08-27	llama : more tokenizer fixes (#2810)	Georgi Gerganov
2023-08-25	ROCm Port (#1087)	Henri Vasserman
2023-08-23	llm : add Falcon support (#2717)	Georgi Gerganov
2023-08-23	Strided perplexity (#2714)	Kawrakow
2023-08-22	CUDA: use mul_mat_q kernels by default (#2683)	Johannes Gäßler
2023-08-22	ggml-cuda : use graph allocator (#2684)	slaren
2023-08-21	gguf : new file format with flexible meta data (beta) (#2398)	Georgi Gerganov