aya-vision-32b
Support summary
aya-vision-32b is a checkpoint published by Cohere, built on the AyaVisionForConditionalGeneration architecture. vLLM last documented support in 0.24.0; its newest indexed release does not list it.
vLLM documents support in 14 of 20 indexed releases, from 0.17.0 to 0.24.0.
- License
- cc-by-nc-4.0
Hugging Face model card
- Publisher
- Cohere
- Task
- image text to text
- License
- cc-by-nc-4.0
- Library
- transformers
- Architecture
- AyaVisionForConditionalGeneration
- Weight tensor elements
- 33.1B
- Tensor types
- F16
- Languages
- en, fr, de, es, it, pt, ja, ko, zh, ar, el, fa, pl, id, cs, he, hi, nl, ro, ru, tr, uk, vi
- Weight access
- Publisher approval or terms required
- Repository created
- 2025-03-02
Model notes and sources
- vLLM v0.24.0 · docs/models/supported_models.md · 14 indexed revisions, v0.17.0 to v0.24.0
- CohereLabs/aya-vision-32b · publisher model card
- CohereLabs/aya-vision-32b · Hugging Face metadata
- Reviewed
Engine support
3 engines
| Engine | Release | Checkpoint support | Evidence scope | Last known supported |
|---|---|---|---|---|
| vLLM | 0.28.0Newest indexed | No matching evidence curated | View 0.24.0 · checkpoint evidenceSource: vLLM v0.24.0 · docs/models/supported_models.mdReviewed | |
Features, dependencies and evidence for vLLM 0.28.0 | ||||
| SGLang | 0.5.19Newest indexed | No matching evidence curated | No supported release indexed | |
Features, dependencies and evidence for SGLang 0.5.19 | ||||
| TensorRT-LLM | 1.2.1Newest indexed | No matching evidence curated | No supported release indexed | |
Features, dependencies and evidence for TensorRT-LLM 1.2.1 | ||||