1562 Commits

This Branch

This Branch

All Branches

Author	SHA1	Message	Date
Alex Cheema	f55a53ae7e	one token at a time	2024-12-16 19:49:52 +00:00
blindcrone	cfedcec3a6	Merge pull request #558 from blindcrone/topology-on-change ... Only collect topology if peers changed v1.0	2024-12-15 05:00:12 -08:00
Nel Nibcord	470f961fbb	Only collect topology if peers changed	2024-12-15 02:50:34 -08:00
Gary	25b4af70e0	Merge branch 'main' into runners	2024-12-14 20:48:58 +00:00
Alex Cheema	a93092105c	set max-generate-tokens to 250	2024-12-14 19:10:03 +00:00
Alex Cheema	0c6ab35333	increase timeout of http request in bench.py up to 10 mins	2024-12-14 18:33:41 +00:00
Alex Cheema	72be5e4bd5	Merge pull request #556 from exo-explore/fixtestmodelhelpers ... fix counts in testmodelhelpers	2024-12-13 21:29:18 +00:00
Alex Cheema	b0e079b36a	fix counts in testmodelhelpers	2024-12-13 17:46:44 +00:00
Alex Cheema	e5d54c77a9	add llama-3.3-70b to 3 M4 Pro cluster	2024-12-12 18:51:26 +00:00
Alex Cheema	2ff4638122	Merge remote-tracking branch 'origin/main' into runners	2024-12-12 17:14:40 +00:00
Alex Cheema	342b5d8ac0	Merge pull request #555 from exo-explore/modelvariations ... add llama-3.2-1b-8bit, llama-3.2-3b-8bit, llama-3.2-3b-bf16	2024-12-12 17:14:28 +00:00
Alex Cheema	a0bada3b2a	add llama-3.2-1b-8bit, llama-3.2-3b-8bit, llama-3.2-3b-bf16	2024-12-12 17:13:34 +00:00
Alex Cheema	b6f2385c41	run llama-3.1-8b on 3 m4 pro cluster	2024-12-12 15:13:10 +00:00
Alex Cheema	9472ab0d2c	t	2024-12-12 15:05:55 +00:00
Alex Cheema	dbb7ad3c08	run with three m4 pro	2024-12-12 14:36:18 +00:00
Alex Cheema	2abe57be21	grasping at straws	2024-12-12 12:03:20 +00:00
Alex Cheema	eeecdcb409	try a different taskpolicy	2024-12-12 11:45:01 +00:00
Alex Cheema	f9f76129a1	better bench system info	2024-12-12 11:34:37 +00:00
Alex Cheema	8c6d37d9b8	m4 cluster test	2024-12-12 11:13:13 +00:00
Alex Cheema	2f74ea112e	Merge pull request #542 from wbic16/fix-issue-458 ... Support CPU-Only CLANG	2024-12-12 10:49:36 +00:00
Alex Cheema	1194db6e65	m3	2024-12-12 00:02:20 +00:00
Alex Cheema	8cb7327da2	re-enable m4 cluster run	2024-12-12 00:01:14 +00:00
Alex Cheema	bba0aa0877	single node test 20	2024-12-11 22:58:44 +00:00
Alex Cheema	279354a1fd	single node test 19	2024-12-11 22:58:38 +00:00
Alex Cheema	92e2b74902	single node test 18	2024-12-11 22:58:33 +00:00
Alex Cheema	76196b8c2f	single node test 17	2024-12-11 22:58:27 +00:00
Alex Cheema	8408c8499f	single node test 16	2024-12-11 22:58:21 +00:00
Alex Cheema	c65d1d9141	single node test 15	2024-12-11 22:58:16 +00:00
Alex Cheema	0bd44c0f78	single node test 14	2024-12-11 22:58:10 +00:00
Alex Cheema	f22bc99f2c	single node test 13	2024-12-11 22:58:04 +00:00
Alex Cheema	3fda05aa39	single node test 12	2024-12-11 22:57:58 +00:00
Alex Cheema	6c322ac070	single node test 11	2024-12-11 22:57:53 +00:00
Alex Cheema	c5c27a32af	single node test 10	2024-12-11 22:57:47 +00:00
Alex Cheema	9f1393dc7f	single node test 9	2024-12-11 22:57:42 +00:00
Alex Cheema	32ff3ef9af	single node test 8	2024-12-11 22:57:36 +00:00
Alex Cheema	b23c3fdaad	single node test 7	2024-12-11 22:57:31 +00:00
Alex Cheema	8b47a9d017	single node test 6	2024-12-11 22:57:25 +00:00
Alex Cheema	f89b85b3f2	single node test 5	2024-12-11 22:57:19 +00:00
Alex Cheema	6f097c9321	single node test 4	2024-12-11 22:57:14 +00:00
Alex Cheema	fb7a0defe1	single node test 3	2024-12-11 22:57:08 +00:00
Alex Cheema	fe506a53d9	single node test 2	2024-12-11 22:57:02 +00:00
Alex Cheema	3f6ef1c763	single node test 1	2024-12-11 22:56:56 +00:00
Alex Cheema	e63c224c71	testtt	2024-12-11 22:53:02 +00:00
Alex Cheema	20e3065e57	les goh	2024-12-11 22:49:29 +00:00
Alex Cheema	83892d5b7e	t	2024-12-11 22:45:59 +00:00
Alex Cheema	83470a98b4	t	2024-12-11 22:42:02 +00:00
Alex Cheema	92edfa5efc	t	2024-12-11 22:40:47 +00:00
Alex Cheema	225dcba788	t	2024-12-11 22:37:11 +00:00
Alex Cheema	6249bee793	tes	2024-12-11 22:35:30 +00:00
Alex Cheema	741c31836e	test	2024-12-11 22:27:10 +00:00