rwkv7
RWKV-X is a Linear Complexity Hybrid Language Model based on the RWKV architecture, integrating Sparse Attention to improve the model's long sequence processing capabilities.
RWKV-7 FP8 quantized inference - 6.4x decode speedup on Blackwell GPUs with <0.3% accuracy loss. Full FP8 E4M3 weight quantization with fused Triton kernels.
High-performance RWKV inference and serving framework, aligned with vLLM design, providing an OpenAI-compatible API with Continuous Batching.
