Commit graph

  • 5b3c637117 Fix for get_agents_session Sarthak Deshpande 2024-10-24 11:35:57 +05:30
  • afa0c2b146 address comments Xi Yan 2024-10-23 22:17:38 -07:00
  • 05a8d47b98 Add a meta-reference-quantized-gpu distribution Ashwin Bharambe 2024-10-23 19:33:14 -07:00
  • 3796dbd4a5 add test for structured output Dinesh Yeduguru 2024-10-23 20:44:49 -07:00
  • f5dcc03742 use pytorch/pytorch as base Xi Yan 2024-10-23 20:22:00 -07:00
  • 4a073fcee5 refactor get_max_tokens and build_options Dinesh Yeduguru 2024-10-23 19:11:04 -07:00
  • 59c93548bc validate scorer input Xi Yan 2024-10-23 17:43:41 -07:00
  • 0ee82571a8 refactor Xi Yan 2024-10-23 17:30:10 -07:00
  • 7c803cef86 update scoring test Xi Yan 2024-10-23 17:22:48 -07:00
  • 302555b11a Implement embeddings for ollama krgutha 2024-10-23 17:18:08 -07:00
  • 3c6555c408 score batch Xi Yan 2024-10-23 16:38:00 -07:00
  • eb572faf6f score batch impl Xi Yan 2024-10-23 16:19:25 -07:00
  • 4b1d7da030 equality scorer Xi Yan 2024-10-23 16:07:17 -07:00
  • cad8c8710b Merge branch 'main' into evals_5 Xi Yan 2024-10-23 15:33:36 -07:00
  • caf253e08f Merge branch 'main' into evals_5 Xi Yan 2024-10-23 15:33:00 -07:00
  • 0cec86453b
    Fix issue w/ routing_table api getting added when router api is not specified (#298) Xi Yan 2024-10-23 15:27:22 -07:00
  • cc508a6fcc inference only yaml Xi Yan 2024-10-23 15:22:03 -07:00
  • 47d9030542 cleanup Xi Yan 2024-10-23 15:19:41 -07:00
  • 07d45f2af3 fix issue w/ enforcing api Xi Yan 2024-10-23 15:15:52 -07:00
  • 35981a1a3b scorer wip Xi Yan 2024-10-23 15:02:54 -07:00
  • 70c08e694d basic scoring function works Xi Yan 2024-10-23 14:42:28 -07:00
  • 38e31ab525 clean up Xi Yan 2024-10-23 14:08:21 -07:00
  • 5930a92dc7 datasetio client Xi Yan 2024-10-23 14:04:51 -07:00
  • 51d5ad67c4 test client: Xi Yan 2024-10-23 13:55:55 -07:00
  • bb43369521 dataset client Xi Yan 2024-10-23 13:53:58 -07:00
  • c5db025320 error checking Xi Yan 2024-10-23 13:17:47 -07:00
  • d8bbce6f7c comments Xi Yan 2024-10-23 13:16:08 -07:00
  • 5e1323b5bf clean up test Xi Yan 2024-10-23 13:08:42 -07:00
  • 555f6e1531 cleanup Xi Yan 2024-10-23 13:07:15 -07:00
  • 92e32f80ad test_scoring Xi Yan 2024-10-23 13:01:49 -07:00
  • 5965ef3979 remove unused imports Dinesh Yeduguru 2024-10-23 12:12:30 -07:00
  • 7c280e18fb dataset validation Xi Yan 2024-10-23 12:08:39 -07:00
  • 5570a63248 completion() for tgi Dinesh Yeduguru 2024-10-23 12:06:25 -07:00
  • 21f2e9adf5
    dont set num_predict for all providers (#294) Dinesh Yeduguru 2024-10-23 11:44:04 -07:00
  • 07e9da19b3 Added in registry and tests passed Sarthak Deshpande 2024-10-23 23:45:01 +05:30
  • dbbfaf68cd dont set num_predict for all providers Dinesh Yeduguru 2024-10-23 10:54:25 -07:00
  • c2d74188ee Added Pinecone Memory Adapter Sarthak Deshpande 2024-10-23 13:16:36 +05:30
  • ffb561070d
    Support structured output for Together (#289) Ashwin Bharambe 2024-10-22 22:36:38 -07:00
  • c7cbd7bf8a Fix typo egad; works now Ashwin Bharambe 2024-10-22 22:35:30 -07:00
  • dbfb10973f WIP support structured output for Together Ashwin Bharambe 2024-10-22 22:30:54 -07:00
  • aefa84e70a wip Xi Yan 2024-10-22 20:00:43 -07:00
  • 2e5e46d896
    Added tests for persistence (#274) Sarthak Deshpande 2024-10-23 08:11:46 +05:30
  • c992ce385b pre-commit changes Sarthak Deshpande 2024-10-23 07:40:49 +05:30
  • 821810657f
    [Evals API][2/n] datasets / datasetio meta-reference implementation (#288) Xi Yan 2024-10-22 16:12:16 -07:00
  • d6df949049 naming fix Xi Yan 2024-10-22 15:57:47 -07:00
  • f131c28db7 address comments Xi Yan 2024-10-22 15:08:57 -07:00
  • cf90ba444d delete dataset_utils Xi Yan 2024-10-22 15:04:28 -07:00
  • bd39b22717 address comments Xi Yan 2024-10-22 14:13:00 -07:00
  • 8a01b9e40c
    Added implementations for get_agents_session, delete_agents_session and delete_agents (#267) Sarthak Deshpande 2024-10-23 02:20:43 +05:30
  • 95aef814af config Xi Yan 2024-10-22 13:21:18 -07:00
  • f8d9e4f60f dataset datasetio Xi Yan 2024-10-22 13:09:17 -07:00
  • 79526f9dd6 pre-commit changes Sarthak Deshpande 2024-10-23 01:34:03 +05:30
  • b81a3bd46a
    Fix import conflict for SamplingParams (#285) Suraj Subramanian 2024-10-22 15:56:00 -04:00
  • c06718fbd5
    Add support for Structured Output / Guided decoding (#281) Ashwin Bharambe 2024-10-22 12:53:34 -07:00
  • 4c3d33e6f4
    feat: Qdrant Vector index support (#221) Anush 2024-10-23 01:20:19 +05:30
  • bc27046f36
    chore: review update with score_threshold Anush008 2024-10-23 00:54:47 +05:30
  • e8de70fdbe skeleton dataset / datasetio Xi Yan 2024-10-22 11:22:39 -07:00
  • 668a495aba
    Add REST api example for chat_completion (#286) Suraj Subramanian 2024-10-22 13:35:20 -04:00
  • d1bef44e2b
    Discard changes to README.md Anush 2024-10-22 22:08:13 +05:30
  • e45f121c77
    [Evals API] [1/n] Initial API (#287) Xi Yan 2024-10-22 09:31:19 -07:00
  • a4f5f1f890 move jobs, fix errors Xi Yan 2024-10-22 09:30:08 -07:00
  • 1575578446
    Merge branch 'meta-llama:main' into qdrant Anush 2024-10-22 21:45:31 +05:30
  • 5836c09c57 scoring functions + evals Xi Yan 2024-10-22 08:53:46 -07:00
  • 1dc2962a33 kill reward scoring Xi Yan 2024-10-22 08:48:08 -07:00
  • 02f4c3a081 datasetio api Xi Yan 2024-10-22 08:42:29 -07:00
  • 37442a495b fix Xi Yan 2024-10-22 08:25:47 -07:00
  • e709101f5b datasets api Xi Yan 2024-10-22 08:24:14 -07:00
  • 287623b513 type system api Xi Yan 2024-10-22 08:16:14 -07:00
  • b279d3bc58
    Update README.md Xi Yan 2024-10-22 08:01:33 -07:00
  • caa30a0b66
    Add REST api example for chat_completion Suraj Subramanian 2024-10-22 10:45:20 -04:00
  • 4a4372b0f1
    Fix import conflict for SamplingParams Suraj Subramanian 2024-10-22 10:32:18 -04:00
  • 1761999dec pre-commit changes Sarthak Deshpande 2024-10-22 18:31:31 +05:30
  • c87c5b568a pre-commit changes Sarthak Deshpande 2024-10-22 18:24:03 +05:30
  • 510269e4c5 add support for TGI Ashwin Bharambe 2024-10-21 23:26:31 -07:00
  • fe20a69f24 Add support for fireworks Ashwin Bharambe 2024-10-21 22:42:29 -07:00
  • cd84dee3e9 Fix and add a test Ashwin Bharambe 2024-10-21 22:02:37 -07:00
  • 40ba22f4c8 add response format to signature Ashwin Bharambe 2024-10-21 19:14:52 -07:00
  • 6d26bbdce3 guided decoding initial draft Ashwin Bharambe 2024-10-21 18:44:19 -07:00
  • 1d241bf3fe
    add completion() for ollama (#280) Dinesh Yeduguru 2024-10-21 22:26:33 -07:00
  • 042f887e8a add completion() for ollama Dinesh Yeduguru 2024-10-21 22:00:16 -07:00
  • e2a5a2e10d
    first version of readthedocs (#278) raghotham 2024-10-22 10:15:58 +05:30
  • dbb5ce43fc Bump version to 0.0.43 Xi Yan 2024-10-21 19:10:01 -07:00
  • a2ff74a686 telemetry WARNING->WARN fix Xi Yan 2024-10-21 18:52:48 -07:00
  • b1451afbc8
    Update README.md Xi Yan 2024-10-21 18:21:30 -07:00
  • 4d2bd2d39e
    add more distro templates (#279) Xi Yan 2024-10-21 18:15:08 -07:00
  • 8025209576 fireworks verified Xi Yan 2024-10-21 18:13:05 -07:00
  • 4a431bd244 fireworks compose up Xi Yan 2024-10-21 18:12:34 -07:00
  • c52ba17d7b fireworks distro Xi Yan 2024-10-21 18:11:52 -07:00
  • 69d7011ed6 readme Xi Yan 2024-10-21 18:01:20 -07:00
  • 74b7a8cb2e together distro verified Xi Yan 2024-10-21 17:50:18 -07:00
  • abde9c1888 verify dockers Xi Yan 2024-10-21 17:23:44 -07:00
  • 68046e25a1 fixing pre-commit issues Raghu Murthy 2024-10-22 05:53:33 +05:30
  • b23cf84eb5 added image Raghu Murthy 2024-10-22 05:48:41 +05:30
  • dec529a5d8 add requirements.txt Raghu Murthy 2024-10-22 04:00:04 +05:30
  • 8cb0368a49 fix path to conf.py Raghu Murthy 2024-10-22 03:58:06 +05:30
  • 60e481284a first version of readthedocs Raghu Murthy 2024-10-22 03:52:45 +05:30
  • cf27d19dd5 fix sse_generator async Xi Yan 2024-10-21 14:03:32 -07:00
  • 1944405dca
    Update new_api_provider.md Ashwin Bharambe 2024-10-21 14:02:51 -07:00
  • 606c48309e Small updates to encourage integration testing Ashwin Bharambe 2024-10-21 13:52:10 -07:00
  • cb203b14b4 update README.md Xi Yan 2024-10-21 13:51:39 -07:00