phoenix-oss/llama-stack
1
0
Fork 0
forked from phoenix-oss/llama-stack-mirror
Code Pull requests Releases Packages 2 Activity Actions

Commit graph

  • e4f14eafe2 Use GPUs 0 and 1 Ashwin Bharambe 2024-11-12 14:21:22 -08:00
  • 1245a625ce Update vllm compose and run YAMLs Ashwin Bharambe 2024-11-12 12:46:32 -08:00
  • afe4a53ae8 Check vLLM registration Ashwin Bharambe 2024-11-12 13:14:36 -08:00
  • 1aeac7b9f7 Change order of building the Docker Ashwin Bharambe 2024-11-12 13:09:04 -08:00
  • 998419ffb2 use image tag actually! Ashwin Bharambe 2024-11-12 12:57:08 -08:00
  • 2c294346ae Update provider types and prefix with inline:: Ashwin Bharambe 2024-11-12 12:54:44 -08:00
  • 896b304e62 Use tags for docker images instead of changing image name Ashwin Bharambe 2024-11-12 12:42:11 -08:00
  • 983d6ce2df
         Remove the "ShieldType" concept (#430) Ashwin Bharambe 2024-11-12 12:37:24 -08:00
  • 09269e2a44
         Enable sane naming of registered objects with defaults (#429) Ashwin Bharambe 2024-11-12 11:18:05 -08:00
  • d9d271a684
         Allow specifying resources in StackRunConfig (#425) Ashwin Bharambe 2024-11-12 10:58:49 -08:00
  • 8035fa1869 versioned persistence key prefixes Dinesh Yeduguru 2024-11-12 10:30:39 -08:00
  • cb77426fb5
         fix fireworks (#427) Xi Yan 2024-11-12 12:15:55 -05:00
  • ec4fcad5ca
         fix eval task registration (#426) Xi Yan 2024-11-12 11:51:34 -05:00
  • 84c6fbbd93
         fix tests after registration migration & rename meta-reference -> basic / llm_as_judge provider (#424) Xi Yan 2024-11-12 10:35:44 -05:00
  • 3d7561e55c
         Rename all inline providers with an inline:: prefix (#423) Ashwin Bharambe 2024-11-11 22:19:16 -08:00
  • f4426f6a43 Fix bug in llama stack build; SERVER_DEPENDENCIES were dropped Ashwin Bharambe 2024-11-11 20:12:13 -08:00
  • 506b99242a Allow specifying TEST / PYPI VERSION for docker name Ashwin Bharambe 2024-11-11 19:55:23 -08:00
  • 36da9a600e add explicit platform Ashwin Bharambe 2024-11-11 19:30:15 -08:00
  • 218803b7c8 add pypi version to docker tag Ashwin Bharambe 2024-11-11 19:14:06 -08:00
  • 47e7c2dc15 Fix openapi generator and regenerator OpenAPI types Ashwin Bharambe 2024-11-11 18:44:38 -08:00
  • 343458479d Make sure TEST_PYPI_VERSION is used in docker builds Ashwin Bharambe 2024-11-11 18:40:13 -08:00
  • 285cd26fb2 Replace colon in path so it doesn't cause issue on Windows Ashwin Bharambe 2024-11-11 17:30:36 -08:00
  • 0a3b3d5fb6
         migrate scoring fns to resource (#422) Dinesh Yeduguru 2024-11-11 17:28:48 -08:00
  • 3802edfc50
         migrate evals to resource (#421) Dinesh Yeduguru 2024-11-11 17:24:03 -08:00
  • b95cb5308f
         migrate dataset to resource (#420) Dinesh Yeduguru 2024-11-11 17:14:41 -08:00
  • 38cce97597
         migrate memory banks to Resource and new registration (#411) Dinesh Yeduguru 2024-11-11 17:10:44 -08:00
  • 6b9850e11b run openapi gen Xi Yan 2024-11-11 18:12:24 -05:00
  • b4416b72fd
         Folder restructure for evals/datasets/scoring (#419) Xi Yan 2024-11-11 17:35:40 -05:00
  • 2b7d70ba86
         [Evals API][11/n] huggingface dataset provider + mmlu scoring fn (#392) Xi Yan 2024-11-11 14:49:50 -05:00
  • b78ee3a0a5
         fix duplicate deploy in compose.yaml (#417) Suraj Subramanian 2024-11-11 13:51:14 -05:00
  • c1f7ba3aed
         Split safety into (llama-guard, prompt-guard, code-scanner) (#400) Ashwin Bharambe 2024-11-11 09:29:18 -08:00
  • 6d38b1690b
         added quickstart w ollama and toolcalling using together (#413) Justin Lee 2024-11-09 10:52:26 -08:00
  • b0b9c905b3 docs Xi Yan 2024-11-09 10:22:41 -08:00
  • cc61fd8083 docs Xi Yan 2024-11-09 09:00:18 -08:00
  • 0c14761453 docs Xi Yan 2024-11-09 08:57:51 -08:00
  • 4986e46188
         Distributions updates (slight updates to ollama, add inline-vllm and remote-vllm) (#408) Ashwin Bharambe 2024-11-08 18:09:39 -08:00
  • ba82021d4b precommit Xi Yan 2024-11-08 17:58:58 -08:00
  • 1ebf6447c5 add missing inits Xi Yan 2024-11-08 17:54:24 -08:00
  • 89c3129f0b add missing inits Xi Yan 2024-11-08 17:49:29 -08:00
  • f6aaa9c708 Bump version to 0.0.50 Xi Yan 2024-11-08 17:28:39 -08:00
  • 65371a5067
         [Docs] Zero-to-Hero notebooks and quick start documentation (#368) Justin Lee 2024-11-08 17:16:44 -08:00
  • ec644d3418
         migrate model to Resource and new registration signature (#410) Dinesh Yeduguru 2024-11-08 16:12:57 -08:00
  • bd0622ef10 update docs Xi Yan 2024-11-08 12:46:43 -08:00
  • 5625aef48a
         Add pip install helper for test and direct scenarios (#404) Dalton Flanagan 2024-11-08 15:18:21 -05:00
  • d800a16acd
         Resource oriented design for shields (#399) Dinesh Yeduguru 2024-11-08 12:16:11 -08:00
  • 7ee9f8d8ac rename Xi Yan 2024-11-08 10:34:48 -08:00
  • b1d7376730 kill tgi/cpu Xi Yan 2024-11-08 10:33:45 -08:00
  • 6192bf43a4
         [Evals API][10/n] API updates for EvalTaskDef + new test migration (#379) Xi Yan 2024-11-07 21:24:12 -08:00
  • 8350f2df4c
         [docs] refactor remote-hosted distro (#402) Xi Yan 2024-11-07 19:16:38 -08:00
  • 345ae07317
         Factor out create_dist_registry (#398) Dalton Flanagan 2024-11-07 16:13:19 -05:00
  • 694c142b89
         Add provider deprecation support; change directory structure (#397) Ashwin Bharambe 2024-11-07 13:04:53 -08:00
  • 36e2538eb0
         fix together inference validator (#393) Xi Yan 2024-11-07 11:31:53 -08:00
  • 31c5fbda5e
         [LlamaStack][Fireworks] Update client and add unittest (#390) Yufei (Benny) Chen 2024-11-07 10:11:28 -08:00
  • cfcc0a871c Slightly update PR template Ashwin Bharambe 2024-11-06 22:49:01 -08:00
  • 489f74a70b Allow simpler initialization of RemoteProviderConfig; fix issue in httpx client Ashwin Bharambe 2024-11-06 19:18:58 -08:00
  • 064d2a5287
         Remove the safety adapter for Together; we can just use "meta-reference" (#387) Ashwin Bharambe 2024-11-06 17:36:57 -08:00
  • 8fc2d212a2
         fix safety signature mismatch (#388) Xi Yan 2024-11-06 16:30:47 -08:00
  • 7c340f0236 rename test_inference -> test_text_inference Ashwin Bharambe 2024-11-06 16:12:50 -08:00
  • 3b54ce3499 remote::vllm now works with vision models Ashwin Bharambe 2024-11-06 16:07:17 -08:00
  • 994732e2e0
         impls -> inline, adapters -> remote (#381) Ashwin Bharambe 2024-11-06 14:54:05 -08:00
  • b10e9f46bb
         Enable remote::vllm (#384) Ashwin Bharambe 2024-11-06 14:42:44 -08:00
  • 093c9f1987
         add bedrock distribution code (#358) Dinesh Yeduguru 2024-11-06 14:39:11 -08:00
  • 6ebd553da5
         fix routing tables look up key for memory bank (#383) Dinesh Yeduguru 2024-11-06 13:32:46 -08:00
  • 748606195b
         Kill llama stack configure (#371) Xi Yan 2024-11-06 13:32:10 -08:00
  • d289afdbde Fix exception in server when client SSE connection closes Ashwin Bharambe 2024-11-06 11:00:34 -08:00
  • cde9bc1388
         Enable vision models for (Together, Fireworks, Meta-Reference, Ollama) (#376) Ashwin Bharambe 2024-11-05 16:22:33 -08:00
  • db30809141 precommit Xi Yan 2024-11-05 15:26:13 -08:00
  • 0706f6c82f add Llama3.2-3B-Instruct:int4-qlora-eo8 Xi Yan 2024-11-05 15:22:26 -08:00
  • 16b7fa4614 quantized model docs Xi Yan 2024-11-05 15:21:13 -08:00
  • 4dd01eeaa1
         fix postgres config validation (#380) Dinesh Yeduguru 2024-11-05 15:09:04 -08:00
  • a2351bf2e9
         add ability to persist memory banks created for faiss (#375) Dinesh Yeduguru 2024-11-05 14:50:23 -08:00
  • dcd8cfe0f3
         add postgres kvstoreimpl (#374) Dinesh Yeduguru 2024-11-05 11:42:21 -08:00
  • 8de845a96d Kill everything from tests/ Ashwin Bharambe 2024-11-04 22:10:16 -08:00
  • f08efc23a6 Kill non-integration older tests Ashwin Bharambe 2024-11-04 22:06:15 -08:00
  • 122793ab92
         Correct a traceback in vllm (#366) Steve Grubb 2024-11-04 23:49:35 -05:00
  • 3ca294c359 Bump version to 0.0.49 Ashwin Bharambe 2024-11-04 20:38:00 -08:00
  • a81178f1f5 The server now depends on SQLite by default Ashwin Bharambe 2024-11-04 20:35:53 -08:00
  • 9a57a009ee Need to await for get_object_from_identifier() now Ashwin Bharambe 2024-11-04 20:32:47 -08:00
  • 7cf4c905f3 add support for remote providers in tests Ashwin Bharambe 2024-11-04 19:57:40 -08:00
  • 0763a0b85f Fix for the fix! Ashwin Bharambe 2024-11-04 20:06:01 -08:00
  • fb2678b134 Fix shield_type and routing table breakage Ashwin Bharambe 2024-11-04 19:40:04 -08:00
  • 657de08f04 precommit Xi Yan 2024-11-04 19:01:56 -08:00
  • 8927da6566 instructions on contributing to readthedocs Xi Yan 2024-11-04 18:57:44 -08:00
  • 4d60ab8531 Bump version to 0.0.48 Xi Yan 2024-11-04 17:37:32 -08:00
  • ffedb81c11
         Significantly simpler and malleable test setup (#360) Ashwin Bharambe 2024-11-04 17:36:43 -08:00
  • 663883cc29
         persist registered objects with distribution (#354) Dinesh Yeduguru 2024-11-04 17:25:06 -08:00
  • c9bf1d7d0b
         pgvector fixes (#369) Dinesh Yeduguru 2024-11-04 17:01:09 -08:00
  • c810a4184d
         [docs] update documentations (#356) Xi Yan 2024-11-04 16:52:38 -08:00
  • ac93dd89cf
         fix bedrock impl (#359) Dinesh Yeduguru 2024-11-03 07:32:30 -08:00
  • bf4f97a2e1 Fix vLLM adapter chat_completion signature Ashwin Bharambe 2024-11-01 13:09:03 -07:00
  • adecb2a2d3 update for message parsing on ios Dalton Flanagan 2024-11-01 14:36:50 -04:00
  • 37b330b4ef
         add dynamic clients for all APIs (#348) Ashwin Bharambe 2024-10-31 14:46:25 -07:00
  • f04b566c5c
         Do not cache pip (#349) Steve Grubb 2024-10-31 12:52:40 -04:00
  • 3b1917d5ea run openapi generator Xi Yan 2024-10-30 16:17:35 -07:00
  • 4aa1bf6a60
         Kill --name from llama stack build (#340) Ashwin Bharambe 2024-10-28 23:07:32 -07:00
  • 26d1668f7d Revert "remove Field for return_type" Ashwin Bharambe 2024-10-28 21:39:39 -07:00
  • eccd7dc4a9 Avoid warnings from pydantic for overriding schema Ashwin Bharambe 2024-10-28 13:36:17 -07:00
  • ed833bb758
         [Evals API][7/n] braintrust scoring provider (#333) Xi Yan 2024-10-28 18:59:35 -07:00
  • ae671eaf7a
         distro readmes with model serving instructions (#339) Xi Yan 2024-10-28 17:47:14 -07:00
  • a70a4706fc
         update distributions compose/readme (#338) Xi Yan 2024-10-28 16:34:43 -07:00