llama.cpp

mirror of https://github.com/ggerganov/llama.cpp.git synced 2024-12-31 22:04:35 +00:00

Author	SHA1	Message	Date
Georgi Gerganov	8f419181d1	common : final touches Some checks failed flake8 Lint / Lint (push) Has been cancelled Details ggml-ci	2024-11-24 19:19:12 +02:00
Georgi Gerganov	7f9cc2058c	common : refactor args ggml-ci	2024-11-24 14:55:16 +02:00
Georgi Gerganov	d9fb3b2e01	speculative : fix the draft sampling ggml-ci	2024-11-24 12:50:17 +02:00
Georgi Gerganov	be5f611000	speculative : do not redraft previous drafts ggml-ci	2024-11-24 12:09:31 +02:00
Georgi Gerganov	ccc8f63f9f	speculative : minor fixup	2024-11-22 13:48:39 +02:00
Georgi Gerganov	f27ddc57d7	speculative : add --draft-min CLI arg Some checks are pending flake8 Lint / Lint (push) Waiting to run Details	2024-11-22 12:27:56 +02:00
Georgi Gerganov	0d4d0c1559	speculative : simplify (cont) ggml-ci	2024-11-22 11:48:32 +02:00
Georgi Gerganov	e4c122b93c	speculative : simplify ggml-ci	2024-11-22 11:07:58 +02:00
Georgi Gerganov	0f878a657c	speculative : manage context in common_speculative Some checks are pending flake8 Lint / Lint (push) Waiting to run Details ggml-ci	2024-11-21 21:27:14 +02:00
Georgi Gerganov	fe043ff1ff	speculative : clean-up and add comments and TODOs [no ci]	2024-11-21 16:09:42 +02:00
Georgi Gerganov	71fc16bb6c	speculative : refactor and add a simpler example ggml-ci	2024-11-21 16:09:40 +02:00