kimi-k2.6-eagle3-mla is an open-source speculative-decoding draft model designed for use with Kimi-K2.6. It features Multi-Head Latent Attention and is compatible with vLLM, enabling faster and more efficient language model inference for AI researchers and developers.
Kimi K2.6 Eagle3 Mla sits in PulseGate's Foundation models & chat category. It focuses on accelerating and optimizing language model inference using speculative decoding techniques. It is built as an open-source project for AI researchers and developers. Kimi K2.6 Eagle3 Mla is open source under the Apache-2.0 license. The product ships for the web and the command line.
Behind Kimi K2.6 Eagle3 Mla is Novita AI, and the product first shipped in 2023. Development happens publicly on GitHub with 39.5k stars. Key capabilities include speculative decoding, Multi-Head Latent Attention, and vLLM compatibility.
Latest indexed changes and source events
novita/kimi-k2.6-eagle3-mla verified by the PulseGate indexer
Other apps tracked under the same category.
