81 Commits

Author	SHA1	Message	Date
jmorganca	cd776e49ad	llama: wip vision support for runner	2024-08-12 22:18:30 -07:00
Daniel Hiltgen	41bf8d9932	Update sync with latest llama.cpp layout, and run against b3485	2024-07-31 09:50:39 -07:00
Daniel Hiltgen	5152a430f5	Prefix all build artifacts with an OS/ARCH dir ... This will help keep incremental builds from stomping on each other and make it easier to stitch together the final runner payloads	2024-07-29 15:38:52 -07:00
jmorganca	7ad4c5334e	clean up metal code	2024-07-29 15:38:52 -07:00
jmorganca	9caee9f8e3	fix Makefile on windows	2024-07-29 15:38:52 -07:00
jmorganca	518ba1c793	remove printing	2024-07-29 15:38:52 -07:00
jmorganca	2abf81885d	lint	2024-07-29 15:38:52 -07:00
jmorganca	f6faf66dac	fix metal	2024-07-29 15:38:52 -07:00
jmorganca	f8424faf75	fix build on windows	2024-07-29 15:38:52 -07:00
jmorganca	295c202b2f	link metal	2024-07-29 15:38:52 -07:00
jmorganca	f96cade3a6	wip	2024-07-29 15:38:52 -07:00
jmorganca	b767f6554c	wip meta	2024-07-29 15:38:52 -07:00
jmorganca	87833dd606	sync	2024-07-29 15:38:52 -07:00
jmorganca	2f94ffd801	remove perl docs	2024-07-29 15:38:52 -07:00
jmorganca	e9d15eb277	remove build scripts	2024-07-29 15:38:52 -07:00
jmorganca	a687913a97	fix output	2024-07-29 15:38:52 -07:00
jmorganca	6110d25dce	arch build	2024-07-29 15:38:52 -07:00
jmorganca	2081ec9ba1	add temporary makefile	2024-07-29 15:38:52 -07:00
jmorganca	34015ca10d	fix cgo flags for darwin amd64	2024-07-29 15:38:51 -07:00
jmorganca	89cb4b8d6b	basic progress	2024-07-29 15:38:51 -07:00
jmorganca	0d365e8d34	add more runner params	2024-07-29 15:38:51 -07:00
jmorganca	424627c347	embeddings	2024-07-29 15:38:51 -07:00
jmorganca	1a801fba2a	remove dependency on llm	2024-07-29 15:38:51 -07:00
jmorganca	727494ea54	grammar	2024-07-29 15:38:51 -07:00
jmorganca	b39fca7088	sampling	2024-07-29 15:38:51 -07:00
jmorganca	db55b1b89d	better example module, add port	2024-07-29 15:38:51 -07:00
jmorganca	1124e24aff	wip	2024-07-29 15:38:51 -07:00
jmorganca	df44d119a3	add llava to runner	2024-07-29 15:38:51 -07:00
jmorganca	aaca2ce093	wip	2024-07-29 15:38:51 -07:00
jmorganca	323a3f1f3a	cuda linux	2024-07-29 15:38:51 -07:00
jmorganca	31e0de825e	disable log file	2024-07-29 15:38:51 -07:00
jmorganca	878eb9a19f	add llava	2024-07-29 15:38:51 -07:00
jmorganca	3d656588a7	avx2 should only add avx2	2024-07-29 15:38:51 -07:00
jmorganca	4dd63c1fef	move runner package down	2024-07-29 15:38:51 -07:00
jmorganca	82214396b5	replace static build in llm	2024-07-29 15:38:51 -07:00
jmorganca	491ff41675	Initial llama Go module	2024-07-29 15:35:09 -07:00
jmorganca	075f2e88d9	add sync of llama.cpp	2024-07-29 15:35:09 -07:00
Michael Yang	fccf8d179f	partial decode ggml bin for more info	2023-08-10 09:23:10 -07:00
Bruce MacDonald	984c9c628c	fix embeddings invalid values	2023-08-09 16:50:53 -04:00
Bruce MacDonald	09d8bf6730	fix build errors	2023-08-09 10:45:57 -04:00
Bruce MacDonald	7a5f3616fd	embed text document in modelfile	2023-08-09 10:26:19 -04:00
Michael Yang	f2074ed4c0	Merge pull request #306 from jmorganca/default-keep-system ... automatically set num_keep if num_keep < 0	2023-08-08 09:25:34 -07:00
Bruce MacDonald	a6f6d18f83	embed text document in modelfile	2023-08-08 11:27:17 -04:00
Jeffrey Morgan	5eb712f962	trim whitespace before checking stop conditions ... Fixes #295	2023-08-08 00:29:19 -04:00
Michael Yang	4dc5b117dd	automatically set num_keep if num_keep < 0 ... num_keep defines how many tokens to keep in the context when truncating inputs. if left to its default value of -1, the server will calculate num_keep to be the left of the system instructions	2023-08-07 16:19:12 -07:00
Michael Yang	b9f4d67554	configurable rope frequency parameters	2023-08-03 22:11:58 -07:00
Michael Yang	c5bcf32823	update llama.cpp	2023-08-03 11:50:24 -07:00
Michael Yang	74a5f7e698	no gpu for 70B model	2023-08-01 17:12:50 -07:00
Michael Yang	319f078dd9	remove -Werror ... there are compile warnings on Linux which -Werror elevates to errors, preventing compile	2023-07-31 21:45:56 -07:00
Jeffrey Morgan	7da249fcc1	only build metal for darwin,arm target	2023-07-31 21:35:23 -04:00