diff --git a/models/moonshotai/Kimi-K2.6.yaml b/models/moonshotai/Kimi-K2.6.yaml index 4bc3f60c..d81d2daa 100644 --- a/models/moonshotai/Kimi-K2.6.yaml +++ b/models/moonshotai/Kimi-K2.6.yaml @@ -37,6 +37,11 @@ features: args: - "--reasoning-parser" - "kimi_k2" + spec_decoding: + description: "Eagle3 speculative decoding for accelerated inference" + args: + - "--speculative-config" + - '{"model":"lightseekorg/kimi-k2.6-eagle3","method":"eagle3","num_speculative_tokens":3}' text_only: description: "Skip loading the vision encoder for text-only workloads — frees VRAM for KV cache. Mutually exclusive with encoder_parallel." args: @@ -48,6 +53,7 @@ features: - "data" opt_in_features: + - spec_decoding - text_only variants: