Commit graph

  • dda20473c5 test action Hardik Shah 2025-01-15 18:06:01 -08:00
  • 20cfac373b test action Hardik Shah 2025-01-15 18:04:47 -08:00
  • 20f0932cbf test action Hardik Shah 2025-01-15 17:58:45 -08:00
  • f34dffaa27 Run notebook test as part of package publish to test-pypi Hardik Shah 2025-01-15 17:56:01 -08:00
  • 5cce5a1f78 nvdia fix Xi Yan 2025-01-15 17:26:31 -08:00
  • c03f7fe9be remove cache Sixian Yi 2025-01-15 17:13:36 -08:00
  • f5076a0a38 undo changes on irrelevant files Sixian Yi 2025-01-15 16:57:32 -08:00
  • 44069404fd stream completion log probs Xi Yan 2025-01-15 16:50:58 -08:00
  • 9c13a7b76b add completion logprobs Xi Yan 2025-01-15 16:48:39 -08:00
  • 901c10d444 address comment Sixian Yi 2025-01-15 16:23:26 -08:00
  • 11b2fdd3d8 support non value for test config Sixian Yi 2025-01-15 13:45:55 -08:00
  • 26d9804efd restructure config Sixian Yi 2025-01-14 16:08:20 -08:00
  • 702cf2d563 [test automation] add support for test config Sixian Yi 2025-01-07 00:14:43 -08:00
  • 4d3f0ae79b [ez] move addoption to conftest in root test directory and fix broken imports Sixian Yi 2025-01-06 21:34:07 -08:00
  • 96edf26a35 memory Xi Yan 2025-01-15 15:59:57 -08:00
  • 7fdc9e04ac fix safety Xi Yan 2025-01-15 15:57:53 -08:00
  • 2c20b88a3f remove prints Xi Yan 2025-01-15 15:56:11 -08:00
  • f9f3303365
    Merge branch 'main' into fix_client_sdk_inference Xi Yan 2025-01-15 15:55:51 -08:00
  • 02a30b669a remove prints Xi Yan 2025-01-15 15:53:52 -08:00
  • 85a3fcee8e fix routing in library client Dinesh Yeduguru 2025-01-15 15:52:21 -08:00
  • da99821989 fix inference sdk test Xi Yan 2025-01-15 15:48:53 -08:00
  • 685baa7f2d fix Sixian Yi 2025-01-15 15:27:23 -08:00
  • b438dad8d2 more idiomatic REST API Dinesh Yeduguru 2025-01-14 14:52:32 -08:00
  • 26bcb9603e comments Xi Yan 2025-01-15 12:52:25 -08:00
  • bae2896528 rebase eval context extraction with query_memory tool Xi Yan 2025-01-15 12:06:49 -08:00
  • b7e59ba002 fix eval test w/ tools Xi Yan 2025-01-15 11:45:59 -08:00
  • 24193f4395 remove assert Xi Yan 2025-01-15 11:18:21 -08:00
  • 6cec64c2e4 fix llama guard Xi Yan 2025-01-15 11:11:31 -08:00
  • cb6c734460 fix nvidia sampling logic Hardik Shah 2025-01-14 18:00:30 -08:00
  • 0edd3ce78b fix tests Hardik Shah 2025-01-14 17:38:10 -08:00
  • d9d827ff25 fix groq util tests Hardik Shah 2025-01-14 16:11:00 -08:00
  • dea575c994 Update Strategy in SamplingParams to be a union Hardik Shah 2025-01-14 15:56:02 -08:00
  • 4f3fd22dd4 add schema type register Xi Yan 2025-01-14 18:08:30 -08:00
  • db5492202f commit Botao Chen 2025-01-14 18:06:37 -08:00
  • a77b8126d0 commit Botao Chen 2025-01-14 18:01:49 -08:00
  • 3da3d26260
    Update Yuan Tang 2025-01-14 20:56:52 -05:00
  • 7c726826b8
    Fix issue when generating vLLM distros Yuan Tang 2025-01-13 18:43:23 -05:00
  • 3097872fd9 remove prints Xi Yan 2025-01-14 16:34:05 -08:00
  • 38c2c9c1dc remove debug print Xi Yan 2025-01-14 16:27:25 -08:00
  • f30c601b10 remove trigger on push Xi Yan 2025-01-14 16:19:44 -08:00
  • 21f1dffba1 fix test version Xi Yan 2025-01-14 16:13:23 -08:00
  • 893276cbb8 test versionings Xi Yan 2025-01-14 16:10:58 -08:00
  • 5c7ac46249 test versionings Xi Yan 2025-01-14 16:09:54 -08:00
  • 48ca00457c test versionings Xi Yan 2025-01-14 16:09:04 -08:00
  • 7f5829036c debug command Xi Yan 2025-01-14 15:44:21 -08:00
  • 63b0a40317 debug command Xi Yan 2025-01-14 15:42:47 -08:00
  • b0833d1376 debug command Xi Yan 2025-01-14 15:40:00 -08:00
  • 3ba0b9f45b debug command Xi Yan 2025-01-14 15:37:18 -08:00
  • 58d38ad3fa no need for dockerfiles Xi Yan 2025-01-14 15:36:46 -08:00
  • 0f21075575 fix tag 2 Xi Yan 2025-01-14 15:24:13 -08:00
  • c144b87049 fix tag Xi Yan 2025-01-14 15:20:45 -08:00
  • d527f3f20b fix tag Xi Yan 2025-01-14 15:18:38 -08:00
  • 28fccb3293 test publish Xi Yan 2025-01-14 15:15:58 -08:00
  • bfb9848074 test publish Xi Yan 2025-01-14 15:12:04 -08:00
  • 0aab982d64 alternative run script Xi Yan 2025-01-14 15:07:58 -08:00
  • 47874e5a25 try run command Xi Yan 2025-01-14 15:03:32 -08:00
  • 3673c98c9a revert back is_terminal Xi Yan 2025-01-14 14:57:03 -08:00
  • 73c428baf4 Fix fireworks run-with-safety template Vladimir Ivic 2025-01-14 14:51:48 -08:00
  • f66109c861 separate step Xi Yan 2025-01-14 14:53:32 -08:00
  • 6cac92cfa3 test Xi Yan 2025-01-14 14:49:15 -08:00
  • d97bcaf625 test Xi Yan 2025-01-14 14:39:37 -08:00
  • 4747c844a2 tmp dockerfile_only flag Xi Yan 2025-01-14 13:59:20 -08:00
  • b197d3ce1c apply change and fixed test cases Edward Ma 2025-01-14 13:24:08 -08:00
  • 20576de6ea Fix broken tests in test_registry Vladimir Ivic 2025-01-14 13:21:32 -08:00
  • 45f4e87f23 commit Botao Chen 2025-01-14 13:15:44 -08:00
  • 96e45d9fca added support of PYPI_VERSION in container.sh Jeff Tang 2025-01-14 13:06:10 -08:00
  • 843c8fab63 added support of PYPI_VERSION in stack build Jeff Tang 2025-01-14 12:15:04 -08:00
  • 8d7bb1140f Merge remote-tracking branch 'origin/main' into support_more_data_format Botao Chen 2025-01-14 11:55:13 -08:00
  • 7fff9434f3 refine Botao Chen 2025-01-14 11:53:57 -08:00
  • 51b4ad77e1 only initialize otel span processors once Dinesh Yeduguru 2025-01-14 10:51:42 -08:00
  • f8d8309b0e fix broken build.py Dinesh Yeduguru 2025-01-14 10:27:04 -08:00
  • 006df17fd6 dont reinstantiate background logger Dinesh Yeduguru 2025-01-14 10:15:11 -08:00
  • ebbb57beae more correct event loop handling for stream Xi Yan 2025-01-14 10:49:51 -08:00
  • a69c1b8bb1 add comment Xi Yan 2025-01-14 10:40:14 -08:00
  • ee2d4a0b89 correct event loop management Xi Yan 2025-01-14 10:39:44 -08:00
  • ba85634758 create new event loop for non-streaming case explicitly Xi Yan 2025-01-14 10:15:45 -08:00
  • 89ab2be302
    Merge branch 'main' into sambanova-inferene snova-edwardm 2025-01-14 10:04:52 -08:00
  • f115ce3edd remove request wrapper Xi Yan 2025-01-14 09:54:19 -08:00
  • 7de832d66c refine Botao Chen 2025-01-13 21:24:25 -08:00
  • d9ceb7067a refine Botao Chen 2025-01-13 21:14:54 -08:00
  • 4c2b05c6b2 refine Botao Chen 2025-01-13 21:11:49 -08:00
  • f4ba0e997a fix provider data Xi Yan 2025-01-13 20:39:28 -08:00
  • a3b1c3438b Merge remote-tracking branch 'origin/main' into support_more_data_format Botao Chen 2025-01-13 20:36:14 -08:00
  • c2c4c96811 addres comment Botao Chen 2025-01-13 20:31:47 -08:00
  • 9e430c253d remove prints Xi Yan 2025-01-13 20:28:31 -08:00
  • d6dd2ba471 fix streaming inline client Xi Yan 2025-01-13 20:16:43 -08:00
  • 7c34c0b763 Update spec Ashwin Bharambe 2025-01-13 20:06:49 -08:00
  • 1ec762f947 move all implementations to use updated type Ashwin Bharambe 2025-01-13 20:04:19 -08:00
  • 16b55666ee introduce and use a generic ContentDelta Ashwin Bharambe 2025-01-13 19:38:44 -08:00
  • 69d886d9cc
    Fix incorrect Python binary path for UBI9 image Yuan Tang 2025-01-13 22:36:13 -05:00
  • 43e3f075b9 Rename ipython to tool Ashwin Bharambe 2025-01-13 18:55:05 -08:00
  • 7d753a7e24 back to scheduled Xi Yan 2025-01-13 17:52:50 -08:00
  • b75dfb0537 test Xi Yan 2025-01-13 17:48:51 -08:00
  • 4b2bd0b685 Consolidating Inference tests under client-sdk tests Vladimir Ivic 2025-01-13 16:18:31 -08:00
  • d26e96a02e fix sqlite span processor Dinesh Yeduguru 2025-01-13 14:25:10 -08:00
  • 643f900535 address feedback Dinesh Yeduguru 2025-01-13 15:04:49 -08:00
  • f3ec272570 [Fireworks] Update model name for Fireworks benjibc 2025-01-13 21:48:04 +00:00
  • c01a89c0e8 Allow build with host network benjibc 2025-01-13 21:44:26 +00:00
  • f8e7d4381e add section to list tools Dinesh Yeduguru 2025-01-13 13:42:58 -08:00
  • 33b4e8df49 Add provider data passing for library client Dinesh Yeduguru 2025-01-13 13:25:36 -08:00