0.5.5

What's Changed

• fixing neuronx dependencies + optimum upgrade by @oOraph in #105
• Compress container with zstd which is way faster than gzip (both for … by @co42 in #107
• Fix entrypoint.sh and kenlm installation by @alvarobartt in #108
• update inferentia2 image by @oOraph in #106
• Bump transformers and sentence-transformers by @alvarobartt in #103

New Contributors

• @oOraph made their first contribution in #105

Full Changelog: 0.5.4...0.5.5

0.5.4

What's Changed

• Bump dependencies and release new version by @alvarobartt in #102

Full Changelog: 0.5.3...0.5.4

0.5.3

What's Changed

• feat(metrics): add /metrics which returns prometheus metrics by @co42 in #95
• Align I/O with Inference API by @alvarobartt in #99
• Fix image-text-to-text provided kwargs to skip tokenizer by @alvarobartt in #100
• Skip pipeline.task check for diffusers and sentence-transformers by @alvarobartt in #101

Full Changelog: 0.5.2...0.5.3

0.5.2

What's Changed

• Bump transformers to 4.46.1 due to 4.46.0 yanked by @alvarobartt in #98

Full Changelog: 0.5.1...0.5.2

0.5.1

What's Changed

• Update by @philschmid in #85
• Update README.md by @philschmid in #86
• New CI by @glegendre01 in #83
• CI move by @glegendre01 in #88
• Pass generator instead of seed to diffusers by @ErikKaum in #89
• Add comment for clarity by @ErikKaum in #90
• Increment Sentence Transformers version to v3.1.1 by @tomaarsen in #91
• Fix: use exec in entrypoint.sh to handle signal correctly via uvicorn by @co42 in #94
• Fix Dockerfile and some minor updates by @alvarobartt in #97
• Set 0.5.1 release with bumped dependencies by @alvarobartt in #96

New Contributors

• @ErikKaum made their first contribution in #89
• @tomaarsen made their first contribution in #91
• @co42 made their first contribution in #94

Full Changelog: 0.5.0...0.5.1

0.5.0

What's Changed

• Create LICENSE by @philschmid in #84

Full Changelog: 0.4.3...0.5.0

0.4.3

What's Changed

• Bump transformers, peft, and diffusers dependencies by @alvarobartt in #79
• Add crcmod to google extras by @alvarobartt in #80
• Release 0.4.3 version with sentence-transformers fixes by @alvarobartt in #81

Full Changelog: 0.4.2...0.4.3

0.4.2

What's Changed

• Update content type by @philschmid in #71
• [Inf2] Add Optimum Neuron support for Encoder models by @philschmid in #73
• Fix _load_repository_from_gcs by @alvarobartt in #76
• Add google extra with google-cloud-storage by @alvarobartt in #77
• Add HF_TRUST_REMOTE_CODE environment variable by @alvarobartt in #78

Full Changelog: 0.4.1...0.4.2

0.4.1

What's Changed

• Add Vertex AI support by @philschmid in #70

Full Changelog: 0.4.0...0.4.1

0.4.0

What's Changed

• Upgrade to Cuda12 and latest versions by @philschmid in #46
• Fix container build pipeline by @rafaelpierrehf in #59
• Build container fix by @rafaelpierrehf in #60
• sha- by @rafaelpierrehf in #62
• peft by @rafaelpierrehf in #64
• change tailscale action version by @glegendre01 in #68

New Contributors

• @rafaelpierrehf made their first contribution in #59

Full Changelog: 0.3.0...0.4.0