Kimi-Audio-7B-Instruct
Support summary
Kimi-Audio-7B-Instruct is a checkpoint published by Moonshot AI, built on the KimiAudioForConditionalGeneration and MoonshotKimiaForCausalLM architectures. vLLM 0.28.0, the newest indexed vLLM release, documents support.
vLLM documents support in 18 of 20 indexed releases, from 0.18.0 to 0.28.0.
- Configured context
- 8,192 tokens
- License
- mit
Hugging Face model card
- Publisher
- Moonshot AI
- Task
- text to speech
- License
- mit
- Library
- kimi-audio
- Architecture
- MoonshotKimiaForCausalLM
- Weight tensor elements
- 9.8B
- Tensor types
- BF16
- Configured context
- 8,192 tokens
- Languages
- en, zh
- Weight access
- Public
- Repository created
- 2025-04-25
Model notes and sources
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 | ||||