diff --git a/models/deepseek-ai/DeepSeek-V4-Pro.yaml b/models/deepseek-ai/DeepSeek-V4-Pro.yaml index 652da054..558b7498 100644 --- a/models/deepseek-ai/DeepSeek-V4-Pro.yaml +++ b/models/deepseek-ai/DeepSeek-V4-Pro.yaml @@ -55,15 +55,10 @@ features: - "--reasoning-parser" - "deepseek_v4" spec_decoding: - description: "Multi-Token Prediction speculative decoding with 2 speculative tokens (1 on Hopper)." + description: "Multi-Token Prediction speculative decoding with 2 speculative tokens." args: - "--speculative_config" - '{"method":"mtp","num_speculative_tokens":2}' - hardware_overrides: - hopper: - args: - - "--speculative_config" - - '{"method":"mtp","num_speculative_tokens":1}' opt_in_features: - spec_decoding