23 Commits

This Branch

This Branch

All Branches

Author	SHA1	Message	Date
mappu	6aadae62aa	doc/README: changelog for v1.1.0	2023-04-09 11:14:47 +12:00
mappu	92987735ae	go mod tidy	2023-04-09 11:14:41 +12:00
mappu	082fb7552a	doc/README: mention GOMAXPROCS is passed through to llama.cpp	2023-04-09 11:14:19 +12:00
mappu	2f4558b68e	api: raise default context size from 512->1024	2023-04-09 11:12:16 +12:00
mappu	fac1a5b484	webui: new style	2023-04-09 11:11:01 +12:00
mappu	527fc92240	webui: add chat-style prompt ... @ref https://github.com/ggerganov/llama.cpp/issues/771#issuecomment-1499900809	2023-04-08 19:22:42 +12:00
mappu	8e378c0734	webui: clamp input area width, default caret to end of textarea	2023-04-08 19:22:30 +12:00
mappu	575f7ac4bc	webui: show current status in the frontend	2023-04-08 16:50:49 +12:00
mappu	5bbd203d31	doc/README: changelog for v1.0.0	2023-04-08 16:15:20 +12:00
mappu	defc784dd8	cflags/arm64: fix mcpu flag syntax	2023-04-08 16:07:58 +12:00
mappu	bb60bb989f	doc/README: update features + api docs	2023-04-08 16:04:55 +12:00
mappu	3ff357b7d4	api: reduce log verbosity, log the time-per-token	2023-04-08 16:04:43 +12:00
mappu	07c5ca1015	webui: autoscroll new messages	2023-04-08 16:04:26 +12:00
mappu	f5ba37a10b	api: simplify/combine the llama_eval branches	2023-04-08 16:04:16 +12:00
mappu	0c96f2bf6b	api: support a MaxTokens parameter	2023-04-08 16:03:59 +12:00
mappu	6c6a5c602e	api: llama_eval only needs to evaluate new tokens	2023-04-08 15:48:38 +12:00
mappu	2c11e32018	api: don't log resulting tokens on backend	2023-04-08 15:48:26 +12:00
mappu	2cdcf54dd8	webui: synchronize context size value for clientside warning	2023-04-08 15:48:16 +12:00
mappu	dc8db75e04	gitignore	2023-04-08 15:31:24 +12:00
mappu	a7dd9580a5	doc/README: initial commit	2023-04-08 15:30:37 +12:00
mappu	fa8db95cc6	doc/license: add MIT license	2023-04-08 15:30:32 +12:00
mappu	d044a9e424	initial commit	2023-04-08 15:30:15 +12:00
mappu	7c6a0cdaa2	llama.cpp: commit upstream files (as of rev 62cfc54f77e5190)	2023-04-08 15:30:02 +12:00