1562 Commits

This Branch

This Branch

All Branches

Author	SHA1	Message	Date
Alex Cheema	719e149aeb	test trigger workflow	2024-07-20 12:45:16 -07:00
Alex Cheema	9d939b3703	disable tinygrad test again, we need a smaller model or a machine with more memory otherwise we get Metal OOM	2024-07-20 12:42:56 -07:00
Alex Cheema	774e620973	add space between outputs in github workflow integration test	2024-07-20 12:40:51 -07:00
Alex Cheema	a2a7ca1f8b	cleaner node info =	2024-07-20 12:33:38 -07:00
Alex Cheema	04f2aa2a65	try with METAL_XCODE=1 for tinygrad metal	2024-07-20 12:16:54 -07:00
Alex Cheema	d2ed4c2a16	disable tinygrad infernece engine test waiting Waiting on https://github.com/tinygrad/tinygrad/issues/5549	2024-07-20 12:13:14 -07:00
Alex Cheema	115aab0d6c	cache tinygrad models in github workflow	2024-07-20 12:12:11 -07:00
Alex Cheema	a4cc667754	async model downloading fixes #30	2024-07-20 12:08:00 -07:00
Alex Cheema	e49924e1b9	add chatgpt-api-response-timeout-secs flag, set this to 20 mins in test	2024-07-20 00:27:14 -07:00
Alex Cheema	7dd7ccab91	do one request to load the model then another to check the response	2024-07-20 00:17:52 -07:00
Alex Cheema	144af10686	separate discovery and chatgpt api integration test	2024-07-20 00:13:19 -07:00
Alex Cheema	93df43d07f	redundant sh	2024-07-20 00:11:05 -07:00
Alex Cheema	bf7aa51ba1	rename to discovery integration test as thats all it checks	2024-07-20 00:09:34 -07:00
Alex Cheema	b9a2c0f730	fix tests	2024-07-20 00:08:45 -07:00
Alex Cheema	d9516d2eb4	insstall in workflow	2024-07-20 00:00:00 -07:00
Alex Cheema	8efd656303	set different api ports so they dont conlict	2024-07-19 23:51:48 -07:00
Alex Cheema	8dd17fe00b	integration test with discovery	2024-07-19 23:51:15 -07:00
Alex Cheema	4d962ffcaa	fix hardcoded path in debug_inference_engine	2024-07-19 23:44:42 -07:00
Alex Cheema	30ab126c08	fix test_inference_engine	2024-07-19 23:44:19 -07:00
Alex Cheema	56e5e34ec9	fix invalid escape sequence exo_text	2024-07-19 23:41:06 -07:00
Alex Cheema	62a2407352	github workflow: use python3 consistently	2024-07-19 23:38:25 -07:00
Alex Cheema	ba1916a388	github workflow for tests	2024-07-19 23:37:15 -07:00
Alex Cheema	10a043773f	check for the last file that downloads in case it fails part way through	2024-07-19 22:16:10 -07:00
Alex Cheema	1475c735c9	fix inference_state serialization. related: #40 #44 #45	2024-07-19 21:39:57 -07:00
Alex Cheema	e18549e9e1	rm print	2024-07-19 16:52:13 -07:00
Alex Cheema	0c5a927f9a	spacing in viz	2024-07-19 16:43:38 -07:00
Alex Cheema	9fa0cb1ab1	add gpu poor/rich bar in panel. fixes #33	2024-07-19 16:35:48 -07:00
Alex Cheema	5b8f127bf4	fix opaque broadcast	2024-07-19 11:37:02 -07:00
Alex Cheema	a342e1abd8	add web url and chatgpt api endpoint to panel (fixes #43), fix a rounding error in the partition to shard mapping implementation	2024-07-19 11:30:13 -07:00
Alex Cheema	8939f888eb	remove spammy log	2024-07-19 10:36:25 -07:00
Alex Cheema	d9484906a3	remove the spammy logs	2024-07-18 23:22:09 -07:00
Alex Cheema	dd09c59719	fix issues with chatgpt api where it would generate too long output. avoid nonlocal	2024-07-18 23:16:59 -07:00
Alex Cheema	4b592f9d45	exo topology visualisation that shows the topology of the network, device capabilities and the currently active node using opaque statuses. fixes #36. ready for #33	2024-07-18 22:50:18 -07:00
Alex Cheema	35177690bd	by default find an ephemeral node port fixes #35, more robust topology updates. both fix #15 and #14	2024-07-18 19:59:57 -07:00
Alex Cheema	54c98607ef	more robust grpc discovery with asyncio and proper error handling, add flops to device capabilities. fixes #23 and progress on #33	2024-07-18 19:06:23 -07:00
Alex Cheema	fa9d416955	rm unused imports	2024-07-18 16:20:01 -07:00
Alex Cheema	0af164f076	remove old PartitioningStrategy	2024-07-18 16:19:20 -07:00
Alex Cheema	1b194b43f6	reference the code for each feature listed in README	2024-07-18 16:18:01 -07:00
Alex Cheema	945f90f676	allow overriding inference_engine and separate flag for TINYGRAD_DEBUG	2024-07-18 16:09:37 -07:00
Alex Cheema	47163d22db	broadcast results concurrently fixes #31	2024-07-18 16:09:37 -07:00
Alex Cheema	621a5f5d7b	Add license badge	2024-07-18 16:00:34 -07:00
Alex Cheema	46d618abed	tiny fixes	2024-07-18 04:33:44 -07:00
Alex Cheema	d4f55002ea	sort topology by memory descending (works well for now to workaround #12	2024-07-18 03:44:35 -07:00
Alex Cheema	071b1caa0b	drop exo to 0.0.1 (still experimental)	2024-07-18 01:17:19 -07:00
Alex Cheema	e7dcdac24c	fix exo text	2024-07-18 01:06:18 -07:00
Alex Cheema	17ecf26677	typo bullet point	2024-07-17 23:41:49 -07:00
Alex Cheema	9958ac3917	Make known issues more prominent	2024-07-17 23:41:24 -07:00
Alex Cheema	72fe293729	exo text on start and stop	2024-07-17 21:59:05 -07:00
Alex Cheema	fbbb45c37e	install script	2024-07-17 21:55:37 -07:00
Alex Cheema	3778301b47	add alternative installation through install.sh	2024-07-17 21:13:59 -07:00