We trained and released DSpark speculators for Kimi-K2.6 and Kimi-K2.7-Code on
@huggingface, with native serving support in
@vllm_project.
Across six benchmarks in our batch-size-1 evaluation:
Kimi-K2.6: 2.55× average throughput (+155%)
Kimi-K2.7-Code: 2.36× average throughput (+136%)