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

  • 9d574f4aee
         fix playground for v1 (#799) Xi Yan 2025-01-16 19:32:07 -08:00
  • b2ac29b9da
         fix provider model list test (#800) Hardik Shah 2025-01-16 19:27:29 -08:00
  • 9f14382d82
         meta reference inference fixes (#797) Ashwin Bharambe 2025-01-16 18:17:46 -08:00
  • cb41848a2a disable version check optionally Ashwin Bharambe 2025-01-16 18:14:26 -08:00
  • 38009631bc
         Remove llama-guard in Cerebras template & improve agent test (#798) Xi Yan 2025-01-16 18:11:35 -08:00
  • 0fefd4390a
         Fix tgi adapter (#796) Xi Yan 2025-01-16 17:44:12 -08:00
  • 73215460ba
         add default toolgroups to all providers (#795) Dinesh Yeduguru 2025-01-16 16:54:59 -08:00
  • e88faa91e2
         fix the code execution test in sdk tests (#794) Dinesh Yeduguru 2025-01-16 16:42:25 -08:00
  • 35bf6ea75a
         Pin torchtune pkg version (#791) Botao Chen 2025-01-16 16:31:13 -08:00
  • d1f3b032c9
         cerebras template update for memory (#792) Xi Yan 2025-01-16 16:07:53 -08:00
  • 48b12b9777
         [Test automation] generate custom test report (#739) Sixian Yi 2025-01-16 15:33:50 -08:00
  • 03ac84a829 Update default port from 5000 -> 8321 Ashwin Bharambe 2025-01-16 15:26:48 -08:00
  • f1faa9c924 pop fix Hardik Shah 2025-01-16 14:09:59 -08:00
  • fcd1a57429 update notebook Dinesh Yeduguru 2025-01-16 14:00:48 -08:00
  • a6b9f2cec7
         fix cerebras template (#790) Xi Yan 2025-01-16 13:53:06 -08:00
  • 12c994b5b2
         REST API fixes (#789) Dinesh Yeduguru 2025-01-16 13:47:08 -08:00
  • cee3816609
         Make llama stack build not create a new conda by default (#788) Ashwin Bharambe 2025-01-16 13:44:53 -08:00
  • 59eeaf7f81
         Idiomatic REST API: Telemetry (#786) Dinesh Yeduguru 2025-01-16 12:08:46 -08:00
  • c79b087552
         [test automation] support run tests on config file (#730) Sixian Yi 2025-01-16 12:05:49 -08:00
  • 74e4d520ac un-skip telemetry cells in notebook Hardik Shah 2025-01-16 11:54:25 -08:00
  • 821ac674ab
         Add notebook testing to nightly build job (#785) Hardik Shah 2025-01-16 11:24:50 -08:00
  • 8d30ecb91a
         Idiomatic REST API: Evals (#782) Dinesh Yeduguru 2025-01-16 11:02:42 -08:00
  • 678ab29129
         Idiomatic REST API: Inspect (#779) Dinesh Yeduguru 2025-01-16 10:39:42 -08:00
  • e239280932
         fireworks add completion logprobs adapter (#778) Xi Yan 2025-01-16 10:37:07 -08:00
  • 05f6b44da7
         Fix telemetry (#787) Dinesh Yeduguru 2025-01-16 10:36:13 -08:00
  • 17fd2d2fd0
         Make notebook testable (#780) Hardik Shah 2025-01-15 19:28:17 -08:00
  • b76bef169c
         fix nvidia inference provider (#781) Xi Yan 2025-01-15 18:49:36 -08:00
  • 965644ce68
         [bugfix] fix client-sdk tests for v1 (#777) Xi Yan 2025-01-15 16:06:57 -08:00
  • 8fd9bcb8cd
         fix routing in library client (#776) Dinesh Yeduguru 2025-01-15 15:59:45 -08:00
  • 3e518c049a
         [bugfix] fix inference sdk test for v1 (#775) Xi Yan 2025-01-15 15:52:26 -08:00
  • 67450e4024
         bug fixes on inference tests (#774) Sixian Yi 2025-01-15 15:39:05 -08:00
  • 27e07b44b5 remove inline-nvidia templates Xi Yan 2025-01-15 14:15:56 -08:00
  • b3202bcf77
         add nvidia distribution (#565) cdgamarose-nv 2025-01-16 03:34:43 +05:30
  • 7fb2c1c48d
         More idiomatic REST API (#765) Dinesh Yeduguru 2025-01-15 13:20:09 -08:00
  • 6deef1ece0
         rebase eval test w/ tool_runtime fixtures (#773) Xi Yan 2025-01-15 12:55:19 -08:00
  • d0a25dd453
         [bugfix] fix llama guard parsing ContentDelta (#772) Xi Yan 2025-01-15 11:20:23 -08:00
  • 32d3abe964
         [CICD] Github workflow for publishing Docker images (#764) Xi Yan 2025-01-15 09:01:33 -08:00
  • b78e6675ea llama-stack version alpha -> v1 Ashwin Bharambe 2025-01-15 05:58:09 -08:00
  • a51c8b4efc
         Convert SamplingParams.strategy to a union (#767) Hardik Shah 2025-01-15 05:38:51 -08:00
  • 300e6e2702
         Fix issue when generating distros (#755) Yuan Tang 2025-01-15 08:34:08 -05:00
  • 52a21ce78f
         Free up memory after post training finishes (#770) Botao Chen 2025-01-14 19:19:38 -08:00
  • b2b82d4a90 removing unused script file Hardik Shah 2025-01-14 17:54:22 -08:00
  • 89e3f81520
         Fix fireworks run-with-safety template (#766) Vladimir Ivić 2025-01-14 15:28:55 -08:00
  • 472feea8d4
         Fix broken tests in test_registry (#707) Vladimir Ivić 2025-01-14 14:33:15 -08:00
  • 91907b714e
         added support of PYPI_VERSION in stack build (#762) Jeff Tang 2025-01-14 13:45:42 -08:00
  • e6e4f0858c
         add braintrust to experimental-post-training template (#763) Botao Chen 2025-01-14 13:42:59 -08:00
  • 25c1d9b037
         [post training] define llama stack post training dataset format (#717) Botao Chen 2025-01-14 12:48:49 -08:00
  • a174938fbd
         Fix telemetry to work on reinstantiating new lib cli (#761) Dinesh Yeduguru 2025-01-14 11:31:50 -08:00
  • 194d12b304
         [bugfix] fix streaming GeneratorExit exception with LlamaStackAsLibraryClient (#760) Xi Yan 2025-01-14 10:58:46 -08:00
  • 2c2969f331 Fixes; make inference tests pass with newer tool call types Ashwin Bharambe 2025-01-13 23:16:16 -08:00
  • d9d34433fc Update spec Ashwin Bharambe 2025-01-13 20:06:49 -08:00
  • 9a5803a429 move all implementations to use updated type Ashwin Bharambe 2025-01-13 20:04:19 -08:00
  • aced2ce07e introduce and use a generic ContentDelta Ashwin Bharambe 2025-01-13 19:38:44 -08:00
  • 9ec54dcbe7
         Switch to use importlib instead of deprecated pkg_resources (#678) Yuan Tang 2025-01-13 23:20:02 -05:00
  • 747683a8a2
         Add init files to post training folders (#711) Botao Chen 2025-01-13 20:19:18 -08:00
  • f320eede2b
         Update Cerebras docs to include header (#704) Henry Tu 2025-01-13 23:18:34 -05:00
  • 9173e35bd5
         Fix incorrect Python binary path for UBI9 image (#757) Yuan Tang 2025-01-13 23:17:21 -05:00
  • ee4e04804f
         Rename ipython to tool (#756) Ashwin Bharambe 2025-01-13 19:11:51 -08:00
  • fdcc74fda2
         [#432] Add Groq Provider - tool calls (#630) Aidan Do 2025-01-14 13:17:38 +11:00
  • ace8dd6087
         [CI/CD] more robust re-try for downloading testpypi package (#749) Xi Yan 2025-01-13 17:53:38 -08:00
  • 79f4299653
         Consolidating Safety tests from various places under client-sdk (#699) Vladimir Ivić 2025-01-13 17:46:24 -08:00
  • b0c12d280a
         Consolidating Inference tests under client-sdk tests (#751) Vladimir Ivić 2025-01-13 17:46:02 -08:00
  • 1cc137cf9c
         [Fireworks] Update model name for Fireworks (#753) Yufei (Benny) Chen 2025-01-13 15:53:57 -08:00
  • 314806cde3
         Add provider data passing for library client (#750) Dinesh Yeduguru 2025-01-13 15:12:10 -08:00
  • 6964510dc1
         update notebook to use new tool defs (#745) Dinesh Yeduguru 2025-01-13 15:07:15 -08:00
  • e45592e229
         Support building UBI9 base container image (#676) Yuan Tang 2025-01-13 16:41:56 -05:00
  • 78727aad26
         Improve model download doc (#748) Botao Chen 2025-01-13 00:39:12 -08:00
  • ec8601ce88
         Replaced zrangebylex method in the range method (#521) Sarthak Deshpande 2025-01-12 11:34:34 +05:30
  • 6d85284abd
         [CICD] github workflow to push nightly package to testpypi (#734) Xi Yan 2025-01-10 17:01:51 -08:00
  • 8b2376bfb3
         Add inline vLLM inference provider to regression tests and fix regressions (#662) Fred Reiss 2025-01-10 16:35:16 -08:00
  • ff182ff6de
         rename LLAMASTACK_PORT to LLAMA_STACK_PORT for consistency with other env vars (#744) raghotham 2025-01-10 11:09:49 -08:00
  • 8af6951106
         remove conflicting default for tool prompt format in chat completion (#742) Dinesh Yeduguru 2025-01-10 10:41:53 -08:00
  • 24fa1adc2f
         Expose LLAMASTACK_PORT in cli.stack.run (#722) Yuan Tang 2025-01-10 12:13:49 -05:00
  • 027a46ddd7
         Consolidating Memory tests under client-sdk (#703) Vladimir Ivić 2025-01-10 08:28:37 -08:00
  • 203d36e2db
         Fixed typo in default VLLM_URL in remote-vllm.md (#723) Yuan Tang 2025-01-10 01:34:34 -05:00
  • 96735e961d
         Add persistence for localfs datasets (#557) Vladislav Bronzov 2025-01-10 02:34:18 +01:00
  • 4938f2fe5d
         Check version incompatibility (#738) Ashwin Bharambe 2025-01-09 14:52:06 -08:00
  • ffc6bd4805
         Add X-LlamaStack-Client-Version, rename ProviderData -> Provider-Data (#735) Ashwin Bharambe 2025-01-09 11:51:36 -08:00
  • a5c57cd381
         agents to use tools api (#673) Dinesh Yeduguru 2025-01-08 19:01:00 -08:00
  • 596afc6497
         add --version to llama stack CLI & /version endpoint (#732) Xi Yan 2025-01-08 16:30:06 -08:00
  • a5e6f10e33
         fix links for distro (#733) Xi Yan 2025-01-08 14:47:09 -08:00
  • ca66a1b188
         Update CODEOWNERS - add sixianyi0721 as the owner (#731) Sixian Yi 2025-01-07 21:11:59 -08:00
  • 7a4383e4c1
         add 3.3 to together inference provider (#729) Xi Yan 2025-01-06 15:39:41 -08:00
  • 7a90fc5854
         move DataSchemaValidatorMixin into standalone utils (#720) Xi Yan 2025-01-06 13:25:09 -08:00
  • 0bc5d05243
         remove default logger handlers when using libcli with notebook (#718) Dinesh Yeduguru 2025-01-06 13:06:22 -08:00
  • e86271aeac
         support llama3.1 8B instruct in post training (#698) Botao Chen 2025-01-03 17:33:05 -08:00
  • 485476c29a
         Fix Groq invalid self.config reference (#719) Aidan Do 2025-01-04 10:47:10 +11:00
  • 04d5b9814f
         Fix assert message and call to completion_request_to_prompt in remote:vllm (#709) Yuan Tang 2025-01-03 15:44:49 -06:00
  • 96d8375663
         Fix incorrect entrypoint for broken llama stack run (#706) Yuan Tang 2025-01-03 11:47:10 -06:00
  • 21357a6dee Kill autocomplete slop Ashwin Bharambe 2025-01-03 09:29:09 -08:00
  • 4320b0ebb2
         [Post training] make validation steps configurable (#715) Botao Chen 2025-01-03 08:43:24 -08:00
  • f450a0fd32
         Change post training run.yaml inference config (#710) Botao Chen 2025-01-03 08:37:48 -08:00
  • e1f42eb5a5
         [#432] Add Groq Provider - chat completions (#609) Aidan Do 2025-01-04 03:27:49 +11:00
  • e3f187fb83 Redact sensitive information from configs when printing, etc. Ashwin Bharambe 2025-01-02 11:40:48 -08:00
  • d9f75cc98f
         Import from the right path (#708) Botao Chen 2025-01-02 13:15:31 -08:00
  • 750604c7af
         [Post Training] Fix missing import (#705) Botao Chen 2025-01-02 13:08:20 -08:00
  • b438e616ff kill api key from notebook Ashwin Bharambe 2025-01-02 11:26:19 -08:00
  • 3a269c4635
         [rag evals] refactor & add ability to eval retrieval + generation in agentic eval pipeline (#664) Xi Yan 2025-01-02 11:21:33 -08:00
  • 8e5b336792
         Made changes to readme and pinning to llamastack v0.0.61 (#624) Justin Lee 2025-01-03 03:18:07 +08:00
  • 49ad168336
         [#407] Agents: Avoid calling tools that haven't been explicitly enabled (#637) Aidan Do 2025-01-03 04:21:35 +11:00