Skip to content

Actions: predibase/lorax

Release Charts

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
425 workflow runs
425 workflow runs

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

Support for Embeddings with XLM-RoBERTa and Adapters (#656)
Release Charts #375: Commit 3f108f7 pushed by tgaddair
October 31, 2024 16:42 19s main
October 31, 2024 16:42 19s
Fix absent fp8_kv property on llama and qwen models (#662)
Release Charts #374: Commit c2441e2 pushed by arnavgarg1
October 30, 2024 18:02 13s main
October 30, 2024 18:02 13s
Support FP8 KV Cache (#652)
Release Charts #373: Commit 2ff1c71 pushed by ajtejankar
October 29, 2024 19:41 13s main
October 29, 2024 19:41 13s
Prompt prefix caching for multi-LoRA (#655)
Release Charts #372: Commit 373c3e6 pushed by tgaddair
October 23, 2024 00:31 16s main
October 23, 2024 00:31 16s
Fix PREDIBASE_API_TOKEN env var being thrown away (#654)
Release Charts #371: Commit 71ca771 pushed by joseph-predibase
October 22, 2024 18:37 14s main
October 22, 2024 18:37 14s
Chunked prefill (#653)
Release Charts #370: Commit 6c5ca67 pushed by tgaddair
October 21, 2024 19:04 16s main
October 21, 2024 19:04 16s
feat: Function calling with output schema enforcement (#536)
Release Charts #369: Commit 418b9fa pushed by tgaddair
October 16, 2024 23:37 14s main
October 16, 2024 23:37 14s
change runner 2 (#650)
Release Charts #368: Commit d9ed1a6 pushed by magdyksaleh
October 16, 2024 21:42 17s main
October 16, 2024 21:42 17s
Added backwards compatible field to OpenAI json_object API (#648)
Release Charts #367: Commit 974c2b2 pushed by magdyksaleh
October 16, 2024 21:34 14s main
October 16, 2024 21:34 14s
Release Charts
Release Charts #366: Commit 808127d pushed by magdyksaleh
October 16, 2024 21:10 15s main
October 16, 2024 21:10 15s
Added backwards compatible field to OpenAI json_object API (#648)
Release Charts #365: Commit 974c2b2 pushed by tgaddair
October 16, 2024 19:48 15s main
October 16, 2024 19:48 15s
try using arc runner for build (#646)
Release Charts #364: Commit c8f361e pushed by noyoshi
October 16, 2024 18:26 21s main
October 16, 2024 18:26 21s
Enhance Structured Output Interface (#644)
Release Charts #363: Commit 4fb4d69 pushed by tgaddair
October 16, 2024 17:39 13s main
October 16, 2024 17:39 13s
Fix compile for qwen-2.5-32b (#645)
Release Charts #362: Commit 8ac729b pushed by tgaddair
October 16, 2024 16:55 16s main
October 16, 2024 16:55 16s
Add --disable-sgmv flag (#639)
Release Charts #361: Commit 3818e1a pushed by joseph-predibase
October 16, 2024 00:03 16s main
October 16, 2024 00:03 16s
Release Charts
Release Charts #360: by tgaddair
October 15, 2024 18:01 17s main
October 15, 2024 18:01 17s
Return n choices for chat completions API (#638)
Release Charts #359: Commit bea8834 pushed by tgaddair
October 15, 2024 16:56 13s main
October 15, 2024 16:56 13s
Look for language model lm head (#640)
Release Charts #358: Commit 2a22063 pushed by Infernaught
October 15, 2024 16:56 17s main
October 15, 2024 16:56 17s
pass correct stuff to predibase-reporter (#635)
Release Charts #357: Commit f1ef0ee pushed by magdyksaleh
October 8, 2024 19:09 13s main
October 8, 2024 19:09 13s
Fix cuda graph tracing without lora ranks (#634)
Release Charts #356: Commit 0c1cec2 pushed by tgaddair
October 7, 2024 17:59 17s main
October 7, 2024 17:59 17s
Fix FlashInfer when not using prefix caching (#633)
Release Charts #355: Commit d513ee8 pushed by tgaddair
October 4, 2024 21:50 13s main
October 4, 2024 21:50 13s
Fix punica kernel compilation (#632)
Release Charts #354: Commit a1230a5 pushed by tgaddair
October 4, 2024 18:15 19s main
October 4, 2024 18:15 19s
Fix prefix plumbing and BGMV compiler dimensions (#631)
Release Charts #353: Commit 99891a0 pushed by tgaddair
October 3, 2024 23:56 13s main
October 3, 2024 23:56 13s
Merge weights (#600)
Release Charts #352: Commit 0670556 pushed by tgaddair
October 3, 2024 17:00 14s main
October 3, 2024 17:00 14s
Added ranks 96 and 128 to BGMV kernel (#630)
Release Charts #351: Commit b9294ed pushed by tgaddair
October 3, 2024 16:54 18s main
October 3, 2024 16:54 18s