42 commits

Author	SHA1	Message	Date
Dakota	e6ac3abdcb	add managed vllm server	2025-11-07 13:06:49 -06:00
Dakota	578175a709	fix pre-commit	2025-10-29 14:47:50 -05:00
Dakota	5d6d6bb0dc	add docs :)	2025-10-29 11:26:43 -05:00
Dakota	c3a118f50d	fix tests	2025-10-29 10:55:10 -05:00
Dakota	d5400460e8	made masked logprobs coherently decided on	2025-10-29 10:52:38 -05:00
dmahan93	c483840f59	set prompt logprobs to a masked value	2025-10-26 11:58:55 -07:00
dmahan93	c22f8ca81b	Merge remote-tracking branch 'origin/add-logprob-server-manager-fn' into add-logprob-server-manager-fn	2025-10-24 23:18:37 -07:00
dmahan93	5d662bf1aa	add chat example and fix bug in managed_server	2025-10-24 23:15:56 -07:00
pre-commit-ci[bot]	0d80da5146	[pre-commit.ci] auto fixes from pre-commit.com hooks ... for more information, see https://pre-commit.ci	2025-10-24 20:10:29 +00:00
dmahan93	7bf4cfbf80	add managed server to make grabbing logprobs easier w/ tokenized items	2025-10-24 13:09:46 -07:00
pre-commit-ci[bot]	312f8859e3	[pre-commit.ci] auto fixes from pre-commit.com hooks ... for more information, see https://pre-commit.ci	2025-10-16 18:47:07 +00:00
Dakota	d240dbb3b7	Merge remote-tracking branch 'origin/add-logprob-server-manager-fn' into add-logprob-server-manager-fn	2025-10-16 13:46:03 -05:00
Dakota	134cbc09d0	update openai/trl_vllm server with new fn	2025-10-16 13:45:55 -05:00
pre-commit-ci[bot]	1e6a745491	[pre-commit.ci] auto fixes from pre-commit.com hooks ... for more information, see https://pre-commit.ci	2025-10-16 17:39:04 +00:00
Dakota	c36ec29656	add sglang specific token level logprob handling and server manager/baseline logprob/token fn	2025-10-16 12:38:03 -05:00
Alexey Gorbatovski	35c542328a	Fix infinite loop in wait_for_sem by updating semaphore values inside loop	2025-07-06 00:27:45 +03:00
dmahan93	44b96c7b6c	Add max_n_completions parameter to ServerManager for handling multiple completions ... - Introduced max_n_completions configuration to limit the number of completions requested per server call. - Updated chat_completion and completion methods to split requests exceeding max_n_completions into multiple calls, merging results accordingly. - Enhanced documentation for max_n_completions in ServerManagerConfig.	2025-06-02 11:11:55 -05:00
Shannon Sands	6f6084e513	linting	2025-05-18 16:55:25 -07:00
Shannon Sands	cb08629bcf	fixing error	2025-05-18 16:06:59 -07:00
Shannon Sands	5f36d0c658	debugging	2025-05-18 16:01:38 -07:00
Shannon Sands	76736ec4c2	removed unused	2025-05-17 13:37:55 -07:00
Shannon Sands	c05d9f7f53	added health check flag to skip entirely	2025-05-17 13:36:26 -07:00
Shannon Sands	f84934363c	linting	2025-05-17 13:06:16 -07:00
Shannon Sands	90138376f9	thanks cursor	2025-05-17 13:00:35 -07:00
Shannon Sands	59b08a1aa9	Added flag for chat completion, switch in OpenAI client	2025-05-17 12:59:20 -07:00
Shannon Sands	81534f7c8a	message	2025-05-17 12:50:35 -07:00
Shannon Sands	7dc3938038	changed health check to chat completions since all oai models are compatible with that, and it should work with compatible servers	2025-05-17 12:46:50 -07:00
dmahan93	f7552c9c6f	make default not slurm	2025-05-13 13:11:04 -05:00
dmahan93	553d45cc7e	start servers as healthy so they can get a chance to check...	2025-05-13 11:17:23 -05:00
dmahan93	8b864e9786	move server_type to serverbaseline instead so it can be used as well for server instantiation	2025-05-13 10:21:58 -05:00
dmahan93	6fc356e76e	fix type checking to substantiate an appropriate class instead of the abstract server class	2025-05-13 10:09:36 -05:00
dmahan93	bb658631e9	fix bad import from restructuring...	2025-05-13 09:58:16 -05:00
dmahan93	df62979b90	refactor to not mess up process...	2025-05-13 09:22:07 -05:00
dmahan93	6e9405ba95	Fix bad merge	2025-05-12 20:02:54 -05:00
dmahan93	0aaf59fc9a	add trl server ... add gsm8k example for axolotl checking	2025-05-12 19:04:46 -05:00
dmahan93	96be544228	Merge commit '71e7a5ca27' into add-support-for-custom-api-servers	2025-05-12 18:40:35 -05:00
dmahan93	1aa72d7e7e	Add n kwarg being ignored workaround	2025-05-12 12:06:03 -05:00
hjc-puro	629d8c1731	Merge pull request #14 from NousResearch/2025-05-02-server-cli	2025-05-09 13:37:54 +08:00
dmahan93	8ff48065a3	Update server_manager.py to not continue to API config stuff if serverbaseline is set	2025-05-08 20:18:15 -05:00
dmahan93	70cf61c210	add custom server support	2025-05-08 12:01:49 -05:00
hjc-puro	4348dd2ec1	hide complicated openai config override behavior somewhere else	2025-05-03 14:18:50 -07:00
Dakota Nous	621d00dd80	first commit	2025-04-29 12:10:10 -07:00