1562 Commits

This Branch

This Branch

All Branches

Author	SHA1	Message	Date
Alex Cheema	4f4696e09d	remove calls to updateTotalTokens in tiny, not sure why its there	2024-07-17 20:57:58 -07:00
Alex Cheema	d4e0a7d14b	add endpoint to get number of encoded tokens	2024-07-17 20:57:04 -07:00
Alex Cheema	127b8e011c	dont explicitly specify show_index	2024-07-17 20:32:33 -07:00
Alex Cheema	a94bdbb9bd	serve tinychat static	2024-07-17 20:30:44 -07:00
Alex Cheema	e82dab1d4c	remove tinygrad hidden files	2024-07-17 20:23:02 -07:00
Alex Cheema	c2fcee4387	only retail examples/tinychat from tinygrad subtree	2024-07-17 20:14:46 -07:00
Alex Cheema	e1cb840b31	Merge commit '0870e6bfb0d46d58e29c6d5822e8bf629d03bdcc' as 'tinychat'	2024-07-17 20:12:20 -07:00
Alex Cheema	0870e6bfb0	Squashed 'tinychat/' content from commit fa7e734b4 ... git-subtree-dir: tinychat git-subtree-split: fa7e734b49529f3b436d329279347b541fcf6435	2024-07-17 20:12:20 -07:00
Alex Cheema	d8c40bb4f1	print a warning if stream task ever times out	2024-07-17 19:09:11 -07:00
Alex Cheema	1e1e11cdc6	check if inference_engine has tokenizer before printing with it	2024-07-17 19:05:39 -07:00
Alex Cheema	8df2f4d857	support for streaming from non-tail nodes on chatgpt api, addresses #20	2024-07-17 19:05:02 -07:00
Alex Cheema	8762effaf4	chatgpt api repsonse streaming solves #20	2024-07-17 19:00:18 -07:00
Alex Cheema	5de2ea51f5	default to llama-3-8b and temperature=0 if not provided	2024-07-17 17:12:14 -07:00
Alex Cheema	5c3f0e3ac6	faster initial node discovery	2024-07-17 17:11:50 -07:00
Alex Cheema	8a35fd83f6	support chatgpt api endpoint fron any node #24	2024-07-17 15:37:47 -07:00
Alex Cheema	ba7abb9896	fix ring topology img	2024-07-17 15:14:01 -07:00
Alex Cheema	c432871ef5	replace the ring topology image as it was not rendering sometimes	2024-07-17 15:11:09 -07:00
Alex Cheema	bcab97cb41	instructions for how to force a node to be the tail	2024-07-17 15:00:23 -07:00
Alex Cheema	eb92da2c3e	cleaner chatgpt api impl with async callbacks	2024-07-17 14:50:16 -07:00
Alex Cheema	7c97ef521d	DEBUG should be imported from exo	2024-07-17 14:24:55 -07:00
Alex Cheema	5055e3788d	separate prerequisities seciton / troubleshooting section in installation of readme	2024-07-17 11:54:09 -07:00
Alex Cheema	998d484384	match psutil platform detection might catch some edge cases	2024-07-17 11:48:52 -07:00
Alex Cheema	99d40b1df0	download tinygrad model log	2024-07-17 11:47:47 -07:00
Alex Cheema	35335706d6	Merge pull request #21 from the-alex-b/setup ... Added setup.py so exo is installable	2024-07-17 11:14:31 -07:00
Alex	442c7d8c3e	update readme	2024-07-17 13:22:29 +02:00
Alex	879b969028	Removed requirements.txt	2024-07-17 13:22:12 +02:00
Alex	4ea7db854a	more complete python gitignore template	2024-07-17 13:22:04 +02:00
Alex	bfaeccc7d5	added setup py	2024-07-17 13:21:46 +02:00
Alex Cheema	12fcbc0d4c	switch over to psutil, more robust system detection	2024-07-17 00:53:46 -07:00
Alex Cheema	43fa45990e	Merge pull request #18 from andvarfolomeev/fix/requirements ... fix: syntax error in requirements.txt	2024-07-16 23:21:05 -07:00
Andrey Varfolomeev	7545e0605b	fix: syntax error in requirements.txt	2024-07-17 16:12:38 +10:00
Alex Cheema	6b3727f023	fetch model if doesnt exist on tinygrad	2024-07-16 23:09:42 -07:00
Alex Cheema	b1f3204e80	add Jinja requirement for linux	2024-07-16 22:56:40 -07:00
Alex Cheema	365114ec57	add stars to readme	2024-07-16 22:46:15 -07:00
Alex Cheema	71e00745cc	fix tokenizer inconsistencies	2024-07-16 22:46:15 -07:00
Alex Cheema	c673b4c37b	clarify readme	2024-07-16 21:21:49 -07:00
Alex Cheema	7cb1ba55a4	Clarify readme iOS	2024-07-16 21:19:09 -07:00
Alex Cheema	c819f675cb	fix linux/amd gpu memory, convert to MB	2024-07-16 18:38:57 -07:00
Alex Cheema	e93a319ca4	typo	2024-07-16 18:34:13 -07:00
Alex Cheema	ce46f00059	linux device capabilities	2024-07-16 18:33:29 -07:00
Alex Cheema	dbbc7be57f	remove hard dependency on MLX fixes #8	2024-07-16 18:07:45 -07:00
Alex Cheema	5e8bfc8a90	remove deprecated main_static	2024-07-16 17:57:01 -07:00
Alex Cheema	e049f701ce	debugging instructions in README	2024-07-16 16:59:49 -07:00
Alex Cheema	bde1e53f5f	add license	2024-07-16 14:06:36 -07:00
Alex Cheema	dd8d18128c	add an opaque inference_state that inference engines can use to pass around small state to other devices	2024-07-16 13:05:20 -07:00
Alex Cheema	03ba31c020	wip state	2024-07-16 13:05:20 -07:00
Alex Cheema	ed7672e32c	Update README.md	2024-07-16 08:39:57 -07:00
Alex Cheema	9354081b21	Merge pull request #9 from mattroyer/patch-1 ... Fix broken links	2024-07-16 07:59:31 -07:00
Matt Royer	9324fc15d9	Fix broken links	2024-07-16 07:47:59 -06:00
Alex Cheema	b897fa4420	Typo ring memory weighted partitioning strategy	2024-07-16 02:42:02 -07:00