Commit Graph

  • ef40fdf5c8 fix(build): quote environment variables aarnphm-ec2-dev 2023-06-21 11:28:37 +00:00
  • de665def5c fix(cli): support loading model-id from local path Aaron 2023-06-21 07:25:13 -04:00
  • 84466c2827 fix(infra): move lines to placeholder Aaron Pham 2023-06-20 21:50:21 -04:00
  • e69d3f9ca0 chore: update bug-report Aaron Pham 2023-06-20 21:49:35 -04:00
  • 9c6b43b163 docs: rename camel case to official Hugging Face name (#39) Ikko Eltociear Ashimine 2023-06-21 01:02:03 +09:00
  • d33149d758 fix(log): repr the given LLMConfig in debug mode aarnphm-ec2-dev 2023-06-19 18:19:51 +00:00
  • ca802d9d1a fix: agent log (#37) Aaron Pham 2023-06-19 14:11:39 -04:00
  • 78a537079e infra: bump to dev version of 0.1.9.dev0 [generated] Aaron Pham [bot] 2023-06-19 18:08:32 +00:00
  • 70c7c0a9b7 fix(cli): use correct API for client aarnphm-ec2-dev 2023-06-19 18:04:27 +00:00
  • 6bbbefd06a infra: prepare for release 0.1.8 [generated] v0.1.8 Aaron Pham [bot] 2023-06-19 18:02:08 +00:00
  • 6d43bdbcdb fix(instruct): remove breakpoint aarnphm-ec2-dev 2023-06-19 17:59:44 +00:00
  • 9139e6f290 docs: update README to use OPT as example Aaron 2023-06-19 13:40:10 -04:00
  • 0e3f8d2fba infra: bump to dev version of 0.1.8.dev0 [generated] Aaron Pham [bot] 2023-06-19 17:30:50 +00:00
  • 9a6af97356 infra: prepare for release 0.1.7 [generated] v0.1.7 Aaron Pham [bot] 2023-06-19 17:27:52 +00:00
  • 752c2e60a5 fix: remove direct url reference Aaron 2023-06-19 13:25:29 -04:00
  • feb0c53146 fix(timeout): increase default timeout to avoid asyncio error aarnphm-ec2-dev 2023-06-19 17:01:54 +00:00
  • 58758f8241 fix(dolly_v2): gc collect after import Aaron 2023-06-19 12:28:13 -04:00
  • 4f1fee4bee fix(ci): install towncrier for changelog automation Aaron 2023-06-19 06:32:15 -04:00
  • 1ed0ae7787 fix(log): make sure to configure OpenLLM logs correctly Aaron 2023-06-19 06:16:08 -04:00
  • 2244cce5bd fix(config): __getitem__ to get the value instead of member of class Aaron 2023-06-19 05:34:49 -04:00
  • 622a2fb37d fix: separate hatch config Aaron 2023-06-19 03:29:20 -04:00
  • e3fad40f21 fix(env): make tests with extra-dependencies Aaron 2023-06-18 23:58:03 -04:00
  • 03758a5487 fix(tools): adhere to style guidelines (#31) Aaron Pham 2023-06-18 20:03:17 -04:00
  • a7a6775c68 chore: add banner for OpenLLM Aaron 2023-06-18 05:55:38 -04:00
  • 33d3523e5b chore(readme): update docs and warning notes Aaron 2023-06-18 01:39:15 -04:00
  • 4fcd7c8ac9 integration: HuggingFace Agent (#29) Aaron Pham 2023-06-18 00:13:53 -04:00
  • fe8da4e8a9 fix(tests): ensure_available on tests aarnphm-ec2-dev 2023-06-17 15:12:28 +00:00
  • 8bd7351d3c chore: update new gif Aaron 2023-06-17 10:26:34 -04:00
  • 5a6f42ee99 infra: fix generated release link for towncrier [skip ci] Aaron 2023-06-17 09:19:46 -04:00
  • 9be65a813b infra: bump to dev version of 0.1.7.dev0 [generated] Aaron Pham [bot] 2023-06-17 13:12:46 +00:00
  • ed398c38f8 infra: prepare for release 0.1.6 [generated] v0.1.6 Aaron Pham [bot] 2023-06-17 13:02:47 +00:00
  • 6f724416c0 perf: build quantization and better transformer behaviour (#28) Aaron Pham 2023-06-17 08:56:14 -04:00
  • 233d4697b5 chore: update __all__ to take into _extra_objects Aaron 2023-06-16 18:13:23 -04:00
  • ded8a9f809 feat: quantization (#27) Aaron Pham 2023-06-16 18:10:50 -04:00
  • 19bc7e3116 feat: fine-tuning [part 1] (#23) Aaron Pham 2023-06-16 00:19:01 -04:00
  • b9ff4ab92a chore: flatten examples llm-config Aaron 2023-06-15 18:39:33 -04:00
  • e4b7714756 chore(js): update metadata Aaron 2023-06-15 13:18:05 -04:00
  • 850cf791ef chore: fix README.md Aaron Pham 2023-06-15 09:37:46 -04:00
  • dc50a2e7e5 docs: add LangChain and BentoML Examples (#25) Chaoyu 2023-06-15 03:14:37 -07:00
  • 5e1445218b refactor: toplevel CLI (#26) Aaron Pham 2023-06-15 02:32:46 -04:00
  • 9a6a976ce1 infra: bump to dev version of 0.1.6.dev0 [generated] Aaron Pham [bot] 2023-06-15 06:16:12 +00:00
  • bb425b89d9 infra: prepare for release 0.1.5 [generated] v0.1.5 Aaron Pham [bot] 2023-06-15 06:05:35 +00:00
  • 528f76e1d0 fix(client): using httpx for running calls within async context Aaron 2023-06-15 01:58:49 -04:00
  • b3d924e6d6 fix(dolly): make sure to use GPU when available aarnphm-ec2-dev 2023-06-15 05:52:25 +00:00
  • dfe71d7867 chore(cli): redirect download models into subcontext aarnphm-ec2-dev 2023-06-14 11:44:39 +00:00
  • d7e92ae525 feat(cli): --device all --workers-per-resource Aaron 2023-06-14 06:36:54 -04:00
  • d07cc95ea0 ci: add hatch to dev envs Aaron 2023-06-14 03:46:42 -04:00
  • 123d9c442f infra: bump to dev version of 0.1.5.dev0 [generated] Aaron Pham [bot] 2023-06-14 07:43:54 +00:00
  • f9c0a1093b infra: prepare for release 0.1.4 [generated] v0.1.4 Aaron Pham [bot] 2023-06-14 07:33:16 +00:00
  • be41c23c10 codegen: remove black as dependencies Aaron 2023-06-14 03:22:05 -04:00
  • 50d59cdf8d types: rename interface Aaron 2023-06-14 02:45:15 -04:00
  • 47da1916ad infra: bump to dev version of 0.1.4.dev0 [generated] Aaron Pham [bot] 2023-06-14 05:56:49 +00:00
  • 52d786edc7 infra: prepare for release 0.1.3 [generated] v0.1.3 Aaron Pham [bot] 2023-06-14 05:46:29 +00:00
  • 111d205f63 perf: faster LLM loading Aaron 2023-06-14 01:36:42 -04:00
  • ebcedc35de fix(exception): handle notfound explicitly Aaron 2023-06-13 20:15:38 -04:00
  • 0ab7450e90 chore(types): add hints for LLMRunner Aaron 2023-06-13 20:13:33 -04:00
  • 03c90c2a13 fix(llm): ensure we don't bleed runner options Aaron 2023-06-13 20:05:33 -04:00
  • e3ccf766d7 chore: expose LLMRunner for type Aaron 2023-06-13 19:47:36 -04:00
  • 1194684658 fix(llm): cached load aarnphm-ec2-dev 2023-06-13 14:22:09 +00:00
  • 74c8323e42 docs: update generated with href Aaron 2023-06-13 07:30:43 -04:00
  • ece2b377c0 infra: bump to dev version of 0.1.3.dev0 [generated] Aaron Pham [bot] 2023-06-13 11:24:14 +00:00
  • 398ed85b9b infra: prepare for release 0.1.2 [generated] v0.1.2 Aaron Pham [bot] 2023-06-13 11:14:25 +00:00
  • cb76a894cf feat(metadata): add configuration to metadata endpoint Aaron 2023-06-13 07:09:13 -04:00
  • dd20941050 chore: metadata (#19) Aaron Pham 2023-06-13 04:09:33 -04:00
  • 764d86289c chore(readme): update table with model_ids matrix Aaron 2023-06-12 16:57:24 -04:00
  • b5547bbc97 infra: bump to dev version of 0.1.2.dev0 [generated] Aaron Pham [bot] 2023-06-12 20:30:48 +00:00
  • f85bbec147 infra: prepare for release 0.1.1 [generated] v0.1.1 Aaron Pham [bot] 2023-06-12 20:19:34 +00:00
  • 71070b90b4 chore(metadata): fix model_id to be respected on service.py Aaron 2023-06-12 16:04:52 -04:00
  • 4717989384 fix(tokenizers): allow forking by default Aaron 2023-06-12 15:41:19 -04:00
  • aa8812cf90 fix(build): empty model_id Aaron 2023-06-12 14:29:08 -04:00
  • 30a8c32a53 infra: bump to dev version of 0.1.1.dev0 [generated] Aaron 2023-06-12 14:31:20 -04:00
  • 53a63dbe78 infra: prepare for release 0.1.0 v0.1.0 Aaron 2023-06-12 14:23:26 -04:00
  • f8ebb36e15 tests: fastpath (#17) Aaron Pham 2023-06-12 14:18:26 -04:00
  • 187a5f834f docs: add --model-id command (#18) Chaoyu 2023-06-12 11:03:36 -07:00
  • d3bbb727ea doc: add gif to readme Jian Shen 2023-06-12 15:51:08 +08:00
  • 0fc209da72 chore: bump up dependencies for BentoML Aaron 2023-06-12 01:26:25 -04:00
  • f8e99dd8f5 chore(configuration): clean house implementation Aaron 2023-06-11 18:45:20 -04:00
  • 1847209489 feat(cli): --workers aarnphm-ec2-dev 2023-06-11 15:50:56 +00:00
  • 81d46ca211 feat(type): support annotations aarnphm-ec2-dev 2023-06-11 14:58:17 +00:00
  • 2e453fb005 refactor(configuration): __config__ and perf aarnphm-ec2-dev 2023-06-11 12:53:15 +00:00
  • 17241292da feat(cli): show runtime implementation aarnphm-ec2-dev 2023-06-11 05:29:11 +00:00
  • 06c90c0ba3 docs: update matrix [generated] Aaron 2023-06-11 00:47:14 -04:00
  • 3177781e50 infra: bump to dev version of 0.0.35.dev0 [generated] Aaron Pham [bot] 2023-06-11 04:45:24 +00:00
  • 0552b32456 infra: prepare for release 0.0.34 [generated] v0.0.34 Aaron Pham [bot] 2023-06-11 04:35:30 +00:00
  • a5efb7fcb1 fix(stablelm): running on GPU aarnphm-ec2-dev 2023-06-11 04:28:22 +00:00
  • 8762a56093 revert: broken KeyboardInterrupt change aarnphm-ec2-dev 2023-06-11 04:20:07 +00:00
  • 512cd0715c feat(service): implementing with lifecycle hooks aarnphm-ec2-dev 2023-06-11 04:14:18 +00:00
  • 5a7942574f chore(docs): update docs for to_runner aarnphm-ec2-dev 2023-06-11 03:38:56 +00:00
  • 6a937d8b51 feat(scheduling): custom GPU offload strategy Aaron 2023-06-10 22:57:54 -04:00
  • b22468e8c4 feat(cli): openllm models --show-available Aaron 2023-06-10 20:45:40 -04:00
  • 7d71246322 fix(stablelm): load with BetterTransformers on CPU only Aaron 2023-06-10 20:45:05 -04:00
  • 204a7ab7c9 revert(starcoder): quant 8 aarnphm-ec2-dev 2023-06-10 23:17:42 +00:00
  • bb37f7e238 feat(utils): lazy load modules and fix typo aarnphm-ec2-dev 2023-06-10 22:18:37 +00:00
  • 05fa34f9e6 refactor: pretrained => model_id Aaron 2023-06-10 17:36:02 -04:00
  • 4841051fc5 feat(stablelm): CPU inference Aaron 2023-06-10 07:53:29 -04:00
  • 53296111d0 fix(gpu): enable device_map 'auto' to multi-gpu setup only aarnphm-ec2-dev 2023-06-10 11:38:31 +00:00
  • 66a87ef0b7 infra: bump to dev version of 0.0.34.dev0 [generated] Aaron Pham [bot] 2023-06-10 10:19:02 +00:00
  • 56f50deab6 infra: prepare for release 0.0.33 [generated] v0.0.33 Aaron Pham [bot] 2023-06-10 10:09:12 +00:00
  • 2348946ada fix(starcoder): disable quant 8 aarnphm-ec2-dev 2023-06-10 10:01:43 +00:00
  • 4db141c649 feat(gpu): support passing GPU per LLM aarnphm-ec2-dev 2023-06-10 09:47:16 +00:00