1552 Commits

This Branch

This Branch

All Branches

Author	SHA1	Message	Date
Alex Cheema	1d5c28aed4	(partially) restore exo node equality by forwarding prompts to the dynamically selected head	2024-07-15 22:59:00 -07:00
Alex Cheema	1ec92b731e	README notice about api endpoint	2024-07-15 22:46:06 -07:00
Alex Cheema	108a904ab3	Readme whitespace	2024-07-15 22:36:07 -07:00
Alex Cheema	e17905e295	add global reset	2024-07-15 22:35:54 -07:00
Alex Cheema	de9b89ea29	readme typo	2024-07-15 18:22:42 -07:00
Alex Cheema	199eeb03db	known issues section in readme	2024-07-15 18:22:09 -07:00
Alex Cheema	d2184f583a	keep track of already visited peers in global operations: collect_topology	2024-07-15 15:43:00 -07:00
Alex Cheema	4502da5bc4	readme bug notice	2024-07-15 15:23:58 -07:00
Alex Cheema	f9a201ddbf	docs dir	2024-07-15 11:37:22 -07:00
Alex Cheema	4d43cb9174	logo	2024-07-15 11:37:12 -07:00
Alex Cheema	4e1f01eeec	update links	2024-07-15 11:20:42 -07:00
Alex Cheema	1dea8b9c28	update discord link	2024-07-15 11:15:06 -07:00
Alex Cheema	544c229e8a	discord link	2024-07-15 11:02:13 -07:00
Alex Cheema	98b30e056b	readme tweak	2024-07-15 00:08:42 -07:00
Alex Cheema	963f8eb6a1	better logs for DEBUG>=1	2024-07-14 23:55:27 -07:00
Alex Cheema	a009f7d608	move examples to examples dir	2024-07-14 23:48:20 -07:00
Alex Cheema	b6595bac04	add llama-3-70b to the examples	2024-07-14 23:47:33 -07:00
Alex Cheema	54e8cad2d6	remove uneeded prints	2024-07-14 23:31:18 -07:00
Alex Cheema	c691205591	empty space	2024-07-14 23:29:20 -07:00
Alex Cheema	bcd58938de	clean debug logs	2024-07-14 23:28:55 -07:00
Alex Cheema	b9c323bb07	memory-efficient shard loading	2024-07-14 23:27:57 -07:00
Alex Cheema	53a5b3fc6a	add uuid requirement	2024-07-14 21:46:41 -07:00
Alex Cheema	05b9fa497d	initialize node id to uuid4 if not set	2024-07-14 21:46:30 -07:00
Alex Cheema	ff597d9551	fix discovery	2024-07-14 21:46:13 -07:00
Alex Cheema	a04974168e	fix model import path	2024-07-14 21:46:00 -07:00
Alex Cheema	b8a2a0fbe0	update readme run instruction	2024-07-14 21:26:56 -07:00
Alex Cheema	a933352ac3	add DEBUG flag for controlling debug logs	2024-07-14 21:26:45 -07:00
Alex Cheema	dd882fe6bc	experimental notice	2024-07-14 21:16:20 -07:00
Alex Cheema	c8753ba5fe	reshuffle readme	2024-07-14 21:12:55 -07:00
Alex Cheema	ee5204fbca	readme installation instructions	2024-07-14 21:12:17 -07:00
Alex Cheema	78da11e10b	slightly nicer readme	2024-07-14 21:05:41 -07:00
Alex Cheema	2fc472c8fe	slightly nicer readme	2024-07-14 21:03:48 -07:00
Alex Cheema	8ff3e263a0	slightly nicer readme	2024-07-14 21:02:25 -07:00
Alex Cheema	32f2e36fd3	main rename	2024-07-14 21:01:28 -07:00
Alex Cheema	5bbde22a23	move everything under exo module	2024-07-14 21:00:37 -07:00
Alex Cheema	c851644a43	update requirements, specify exact versions	2024-07-14 20:55:29 -07:00
Alex Cheema	32972033dd	update readme	2024-07-14 18:38:48 -07:00
Alex Cheema	5ef07d41a5	readme	2024-07-14 18:09:38 -07:00
Alex Cheema	490fa102a4	tinygrad inference engine	2024-07-14 13:07:37 -07:00
Alex Cheema	e6f387a690	handle is_finished	2024-07-13 23:27:34 -07:00
Alex Cheema	b01f69bb6b	add support for multiple concurrent requests with request ids	2024-07-13 23:11:01 -07:00
Alex Cheema	7077652c8e	graceful node shutdown	2024-07-13 20:43:37 -07:00
Alex Cheema	ca6095c04d	a generic test for every inference engine	2024-07-13 18:25:26 -07:00
Alex Cheema	850b72d3ea	make StatefulShardedModel callable, add some tests for mlx sharded inference	2024-07-13 15:41:15 -07:00
Alex Cheema	6ee0547eff	fix layer calculation for sharded llama	2024-07-13 15:39:31 -07:00
Alex Cheema	445eda156c	dynamically assign shards to nodes deterministically weighted by memory	2024-06-25 21:17:58 +01:00
Alex Cheema	36b8456798	collect global topology with local peer visibility, ring memory weighted partitioning strategy	2024-06-25 12:32:16 +01:00
Alex Cheema	3a66a0a4a8	add requirements.txt	2024-06-24 21:00:04 +01:00
Alex Cheema	ee96c6b023	add another test for device capabiities on MacBook Air	2024-06-24 20:59:55 +01:00
Alex Cheema	6c8c9ee7b1	topology with partitioning strategy	2024-06-24 20:56:50 +01:00