Eagle2.5-8B
Support summary
Eagle2.5-8B is a checkpoint published by NVIDIA, built on the Eagle2_5_VLForConditionalGeneration architecture. vLLM 0.28.0, the newest indexed vLLM release, documents support.
vLLM documents support in 20 of 20 indexed releases, from 0.17.0 to 0.28.0.
- License
- nsclv1
Hugging Face model card
- Publisher
- NVIDIA
- Task
- image text to text
- License
- nsclv1
- Library
- transformers
- Architecture
- Eagle2_5_VLForConditionalGeneration
- Weight tensor elements
- 8.1B
- Tensor types
- BF16
- Languages
- multilingual
- Base models
- Qwen/Qwen2.5-7B-Instruct, google/siglip2-so400m-patch16-512
- Weight access
- Publisher approval or terms required
- Repository created
- 2025-04-12
Model notes and sources
- vLLM v0.28.0 · docs/models/supported_models.md · 20 indexed revisions, v0.17.0 to v0.28.0
- nvidia/Eagle2.5-8B · publisher model card
- nvidia/Eagle2.5-8B · Hugging Face metadata
- Reviewed
Engine support
3 engines
| Engine | Release | Checkpoint support | Evidence scope | Last known supported |
|---|---|---|---|---|
| vLLM | 0.28.0Newest indexed | Checkpoint evidenceSource: vLLM v0.28.0 · docs/models/supported_models.mdReviewed | 0.28.0This release | |
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 | ||||