Qwen2.5-VL-72B-Instruct
Support summary
Qwen2.5-VL-72B-Instruct is a checkpoint published by Qwen, built on the Qwen2_5_VLForConditionalGeneration architecture. vLLM 0.28.0, the newest indexed vLLM release, documents support. Official recipes or cookbooks cover SGLang, without pinning a stable release. TensorRT-LLM lists its architecture, but not this exact checkpoint.
vLLM documents support in 20 of 20 indexed releases, from 0.17.0 to 0.28.0.
- Documented hardware
- AMD / ROCm and Intel GPU / XPU
- Documented quantization
- BF16
- Documented features
- Tensor parallelism
- Configured context
- 128,000 tokens
- License
- qwen
Hardware, quantization and features count only statements about this checkpoint; engine-wide capabilities are listed with each release.
Hugging Face model card
- Publisher
- Qwen
- Task
- image text to text
- License
- qwen
- Library
- transformers
- Architecture
- Qwen2_5_VLForConditionalGeneration
- Weight tensor elements
- 73.4B
- Tensor types
- BF16
- Configured context
- 128,000 tokens
- Languages
- en
- Weight access
- Public
- Repository created
- 2025-01-27
Model notes and sources
- vLLM v0.28.0 · docs/models/supported_models.md · 20 indexed revisions, v0.17.0 to v0.28.0
- vLLM v0.28.0 · docs/models/hardware_supported_models/xpu.md · 20 indexed revisions, v0.17.0 to v0.28.0
- Qwen/Qwen2.5-VL-72B-Instruct · publisher model card
- Qwen/Qwen2.5-VL-72B-Instruct · Hugging Face metadata
- Qwen/Qwen2.5-VL-72B-Instruct · publisher configuration
- vllm · models/Qwen/Qwen2.5-VL-72B-Instruct.yaml
- sglang · docs/cookbook/autoregressive/Qwen/Qwen2.5-VL.mdx
- vllm · Qwen/Qwen2.5-VL.md
- Reviewed
Engine support
3 engines
| Engine | Release | Checkpoint support | Evidence scope | Last known supported |
|---|---|---|---|---|
| vLLM | Version not pinnedRecipe / cookbook | Documented recipeSource: vllm · models/Qwen/Qwen2.5-VL-72B-Instruct.yamlReviewed | View 0.28.0 | |
Features, dependencies and evidence for vLLM 0.28.0 | ||||
| SGLang | Version not pinnedRecipe / cookbook | Documented recipeSource 1: sglang · docs/cookbook/autoregressive/Qwen/Qwen2.5-VL.mdxSource 2: sglang · docs/src/snippets/autoregressive/qwen25-vl-deployment.jsxReviewed | No supported release indexed | |
Features, dependencies and evidence for SGLang 0.5.19 | ||||
| TensorRT-LLM | 1.2.1Newest indexed | Architecture listed; exact checkpoint unknown | No supported release indexed | |
Features, dependencies and evidence for TensorRT-LLM 1.2.1 | ||||