Skip to content

Actions: predibase/lorax

Release Charts

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
426 workflow runs
426 workflow runs

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

Move NER output formatting to server (#561)
Release Charts #301: Commit efa4bff pushed by magdyksaleh
July 31, 2024 05:42 19s main
July 31, 2024 05:42 19s
Support FP8 for Mistral (#559)
Release Charts #300: Commit 91ef7a8 pushed by ajtejankar
July 30, 2024 22:30 18s main
July 30, 2024 22:30 18s
Added missing nvidia-ml-py package (#558)
Release Charts #299: Commit d1a4d09 pushed by tgaddair
July 26, 2024 19:35 13s main
July 26, 2024 19:35 13s
Allow eager_prefill to be set in Helm chart (#557)
Release Charts #298: Commit 15a38d5 pushed by tgaddair
July 26, 2024 16:32 16s main
July 26, 2024 16:32 16s
Fix the attention bug caused by upgrading vLLM (#555)
Release Charts #297: Commit 2e81331 pushed by ajtejankar
July 26, 2024 03:07 15s main
July 26, 2024 03:07 15s
Update PyTorch, CUDA, vLLM, and Bitsandbytes (#553)
Release Charts #296: Commit 5cefe6e pushed by tgaddair
July 25, 2024 16:44 18s main
July 25, 2024 16:44 18s
Fix: short circuit download, load, offload for preloaded adapters (#552)
Release Charts #295: Commit 07addea pushed by tgaddair
July 23, 2024 22:48 17s main
July 23, 2024 22:48 17s
Apply chat template in router to properly validate input length (#538)
Release Charts #294: Commit 59631a0 pushed by tgaddair
July 23, 2024 17:55 16s main
July 23, 2024 17:55 16s
Add support for Llama 3 rotary embeddings (#551)
Release Charts #293: Commit 240079b pushed by tgaddair
July 23, 2024 17:05 15s main
July 23, 2024 17:05 15s
Tokenize inputs in router (#548)
Release Charts #292: Commit 452ac73 pushed by tgaddair
July 19, 2024 21:51 13s main
July 19, 2024 21:51 13s
Fix : compile bug causing models to error with 'lora' key not found (…
Release Charts #291: Commit 1adc076 pushed by ajtejankar
July 19, 2024 19:26 15s main
July 19, 2024 19:26 15s
Move kv cache allocation to router to ensure correct block allocation…
Release Charts #290: Commit 5a7a1be pushed by tgaddair
July 19, 2024 17:10 17s main
July 19, 2024 17:10 17s
Preload adapters during init (#543)
Release Charts #289: Commit 5c25e26 pushed by tgaddair
July 17, 2024 22:30 18s main
July 17, 2024 22:30 18s
no warm up (#540)
Release Charts #288: Commit 2dd5277 pushed by magdyksaleh
July 15, 2024 23:31 17s main
July 15, 2024 23:31 17s
Fix gemma2 (#539)
Release Charts #287: Commit 35f666a pushed by Infernaught
July 12, 2024 20:42 14s main
July 12, 2024 20:42 14s
Lorax NER (#531)
Release Charts #286: Commit a3ad209 pushed by magdyksaleh
July 9, 2024 13:14 13s main
July 9, 2024 13:14 13s
Infer dtype from model config when not explicitly specified (#534)
Release Charts #285: Commit 24cb494 pushed by arnavgarg1
July 3, 2024 22:48 14s main
July 3, 2024 22:48 14s
bug : fix Qwen-2 sliding_window config bug (#532)
Release Charts #284: Commit ecbe9ea pushed by ajtejankar
July 1, 2024 22:39 12s main
July 1, 2024 22:39 12s
Added Gemma2 (#530)
Release Charts #283: Commit c88fa9e pushed by tgaddair
July 1, 2024 21:12 17s main
July 1, 2024 21:12 17s
bug : fix the type checking errors thrown by new ruff version (#533)
Release Charts #282: Commit 2731478 pushed by ajtejankar
July 1, 2024 17:50 15s main
July 1, 2024 17:50 15s
Bug fix for illegal memory access error caused when running medusa lo…
Release Charts #281: Commit f3a67bb pushed by ajtejankar
June 26, 2024 07:45 17s main
June 26, 2024 07:45 17s
Update development env
Release Charts #280: Commit 3247ef6 pushed by tgaddair
June 24, 2024 23:24 18s main
June 24, 2024 23:24 18s
Added eager prefill option (#524)
Release Charts #279: Commit ee5b7fe pushed by tgaddair
June 24, 2024 18:21 14s main
June 24, 2024 18:21 14s
Disable fp8 kv cache for lovelace (#520)
Release Charts #278: Commit 49bb52f pushed by tgaddair
June 18, 2024 23:20 13s main
June 18, 2024 23:20 13s
docs: update development_env.md (#515)
Release Charts #277: Commit 559fc3b pushed by tgaddair
June 18, 2024 19:01 19s main
June 18, 2024 19:01 19s