61 Commits

This Branch

This Branch

All Branches

Author	SHA1	Message	Date
Rick Zhou	2fdeb4a3e7	Merge pull request #7 from bentoml/pr-mixtral-support ... [Model Support] Support Mixtral 8x7b model	2024-07-02 23:35:20 -07:00
Rick Zhou	6a6d74ad84	Merge pull request #8 from bentoml/pr-local-run-fix ... fix: Fix bug with local run with system prompt	2024-07-02 23:23:32 -07:00
Rick Zhou	c6f5004de6	fix: Fix bug with local run with system prompt	2024-07-03 04:52:12 +00:00
Rick Zhou	1822f5ae17	[Model Support] Support Mixtral 8x7b model	2024-07-03 02:51:26 +00:00
Frost Ming	04a1a87d97	fix: specify the message schema for chat endpoint (#5)	2024-06-27 08:52:40 +08:00
github-actions[bot]	25baeab5dd	Sync chat UI from main repository	2024-06-21 04:16:17 +00:00
Rick Zhou	5e3111e271	chore: update UI serving logic	2024-06-20 18:22:26 +00:00
Rick Zhou	b5341fdb36	fix: make compatible with vllm 0.4.3 API	2024-06-20 17:24:31 +00:00
Rick Zhou	b1ad075795	fix: update chaat UI	2024-06-19 09:07:07 +00:00
bojiang	22f346a06b	Update requirements.txt (#4)	2024-06-17 13:25:06 +08:00
bojiang	d2f1bf76a5	fix: service_home label	2024-06-12 21:37:19 +08:00
bojiang	042492055a	mount ui to /chat	2024-06-12 20:04:14 +08:00
bojiang	f718e045d5	fix: io types	2024-06-12 20:04:14 +08:00
bojiang	c5e8a0af14	fix: chatui	2024-06-12 20:04:14 +08:00
bojiang	dc8a1ef8ee	add chatui	2024-06-12 20:04:14 +08:00
bojiang	ebed5331e3	not work	2024-06-12 20:04:14 +08:00
bojiang	b11140298c	add openai apis	2024-06-12 20:04:14 +08:00
bojiang	1216689743	refactor(openai): simpler integration	2024-06-12 20:04:14 +08:00
bojiang	c7f9fad285	fix openai api	2024-06-12 20:04:14 +08:00
bojiang	b8d536d479	add more qwen versions	2024-06-12 20:04:14 +08:00
bojiang	52c625ec2f	Revert "chore: bump vllm to 0.4.3" (#3)	2024-06-12 20:03:58 +08:00
Aaron Pham	41ad0a9b01	chore: bump vllm to 0.4.3 ... chore: bump vllm to 0.4.3	2024-06-10 22:21:19 -04:00
Zhao Shenyang	bcecbbd918	chore: bump vllm to 0.4.3	2024-06-11 03:20:20 +08:00
Rick Zhou	7a442f2104	Merge pull request #1 from bentoml/rick-0604-pr-chat-template ... feat: Use community chat template as the source of truth. Fall back to HF tokenizer template	2024-06-09 16:03:03 -07:00
bojiang	69597378e7	Delete outlines-integration directory	2024-06-07 11:59:10 +08:00
bojiang	81c12a42f6	add qwen	2024-06-07 11:55:27 +08:00
bojiang	a0bda52299	add source_repo	2024-06-05 13:40:43 +08:00
Rick Zhou	cbde63ab24	feat: Use community chat template as the source of truth. Fall back to HF tokenizer template	2024-06-04 21:33:50 +00:00
bojiang	091829a830	support Python>=3.9	2024-06-04 22:50:30 +08:00
bojiang	9d667bb46a	add more version of llama	2024-06-04 19:54:26 +08:00
bojiang	47fefe30ed	chattts	2024-06-04 18:57:11 +08:00
Rick Zhou	8f27daa058	Update openvllm protocol to be compatible with 0.4.2	2024-06-03 08:15:22 +00:00
bojiang	b165d94fbb	Create README.md	2024-05-31 23:04:18 +08:00
bojiang	91cdc6641a	rm README	2024-05-31 22:50:08 +08:00
bojiang	5df10f7ea1	ignore ChatTTS	2024-05-31 22:49:40 +08:00
bojiang	5e67ca4dcf	fix chattts	2024-05-31 22:48:13 +08:00
bojiang	b8467aa09e	use absolute path	2024-05-31 21:44:47 +08:00
bojiang	a3cc7544d8	add chattts	2024-05-31 21:19:16 +08:00
bojiang	c94a2e0cb0	clean	2024-05-29 13:09:35 +08:00
bojiang	a385e3262f	fix: replace gemma 7b awq chat_template	2024-05-27 18:16:52 +08:00
bojiang	609af2e1f0	feat: add gemma	2024-05-27 18:02:22 +08:00
bojiang	c1fb00c4bd	chore: add more alias	2024-05-27 16:40:31 +08:00
bojiang	193d480b09	fix	2024-05-23 02:00:45 +08:00
bojiang	5db1819527	fix: use official chat_template first	2024-05-21 21:26:05 +08:00
bojiang	d6e99135e0	update dependencies	2024-05-21 04:28:43 +08:00
bojiang	e7e84ad66a	fix template	2024-05-21 04:26:49 +08:00
bojiang	b0f53e2007	opt	2024-05-21 03:11:49 +08:00
bojiang	1860d9880e	try fix chat template for openai api	2024-05-21 02:38:26 +08:00
bojiang	2dcce43165	trailing leading whitespace	2024-05-21 02:30:22 +08:00
bojiang	72068db844	clean old prompts	2024-05-21 02:18:59 +08:00