Skip to content

Actions: predibase/lorax

Release Charts

Actions

Loading...

Show workflow options

Create status badge

278 workflow runs
278 workflow runs
Event

Filter by event

Status

Filter by status

Branch
Actor

Filter by actor

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
try out an integration test workflow (#516)
Release Charts #276: Commit cfc1e19 pushed by noyoshi
June 14, 2024 17:21 14s main
June 14, 2024 17:21 14s
Fix issue with GQA initialization for Qwen2 (#514)
Release Charts #275: Commit 9bed4da pushed by arnavgarg1
June 13, 2024 19:37 14s main
June 13, 2024 19:37 14s
fix batching bug (#513)
Release Charts #274: Commit 835d19c pushed by tgaddair
June 12, 2024 21:38 14s main
June 12, 2024 21:38 14s
Fixed case where loaded lora adapter has no segments (#510)
Release Charts #273: Commit 432be6e pushed by tgaddair
June 12, 2024 04:03 14s main
June 12, 2024 04:03 14s
feat: return usage in ChatCompletionStreamResponse (#506)
Release Charts #272: Commit 4187cab pushed by tgaddair
June 11, 2024 16:33 16s main
June 11, 2024 16:33 16s
Add distilbert (#508)
Release Charts #271: Commit 84fb56d pushed by magdyksaleh
June 10, 2024 22:09 15s main
June 10, 2024 22:09 15s
Bert to gpu (#507)
Release Charts #270: Commit f5e71bd pushed by magdyksaleh
June 10, 2024 21:31 14s main
June 10, 2024 21:31 14s
Add support for batching to embedder models (#503)
Release Charts #269: Commit e8f3d33 pushed by tgaddair
June 8, 2024 05:34 13s main
June 8, 2024 05:34 13s
hqq upgrades (#491)
Release Charts #268: Commit 1b528e0 pushed by tgaddair
June 6, 2024 16:25 14s main
June 6, 2024 16:25 14s
Fixed phi-3 with Su Rotary Embedding (#499)
Release Charts #267: Commit c71861a pushed by tgaddair
June 5, 2024 16:21 15s main
June 5, 2024 16:21 15s
Revert AWQ to stable commit (#498)
Release Charts #266: Commit b2ea56e pushed by tgaddair
June 4, 2024 21:57 13s main
June 4, 2024 21:57 13s
Update Makefile-awq (#493)
Release Charts #265: Commit b1db967 pushed by tgaddair
June 4, 2024 05:23 14s main
June 4, 2024 05:23 14s
Bump client to v0.6.1 (#496)
Release Charts #264: Commit 319183e pushed by tgaddair
June 3, 2024 22:43 16s main
June 3, 2024 22:43 16s
Add retries on common session errors for the client (#495)
Release Charts #263: Commit 0903347 pushed by gyanesh-mishra
June 3, 2024 20:37 14s main
June 3, 2024 20:37 14s
Fix quant cache OOM (#494)
Release Charts #262: Commit 26e0982 pushed by tgaddair
May 30, 2024 05:36 12s main
May 30, 2024 05:36 12s
add missed dtypes for 8bit kv cache (#490)
Release Charts #261: Commit 7d6b1d4 pushed by tgaddair
May 28, 2024 21:13 13s main
May 28, 2024 21:13 13s
Fix issue with Medusa batch load signature (#492)
Release Charts #260: Commit f2193f0 pushed by tgaddair
May 28, 2024 16:19 18s main
May 28, 2024 16:19 18s
Embedder Service v0 with FlashBert (#385)
Release Charts #259: Commit e37549e pushed by tgaddair
May 25, 2024 21:15 12s main
May 25, 2024 21:15 12s
fix: load tokenizer/config with trust_remote_code (#476)
Release Charts #258: Commit feb69c4 pushed by tgaddair
May 25, 2024 20:14 12s main
May 25, 2024 20:14 12s
start porting latest tgi (#480)
Release Charts #257: Commit a2ca687 pushed by tgaddair
May 24, 2024 22:52 12s main
May 24, 2024 22:52 12s
Fix for the LM_HEAD issue (#475)
Release Charts #256: Commit da90421 pushed by tgaddair
May 23, 2024 20:28 13s main
May 23, 2024 20:28 13s
chore: update infer.rs (#487)
Release Charts #255: Commit 2481e70 pushed by tgaddair
May 23, 2024 19:34 15s main
May 23, 2024 19:34 15s
Bump lorax client v0.6.0 (#488)
Release Charts #254: Commit bd7db80 pushed by tgaddair
May 23, 2024 16:44 11s main
May 23, 2024 16:44 11s