vllm.models.deepseek_v41.nvidia

Modules:

• dspark –

  DSpark draft model for DeepSeek-V4.1 (semi-autoregressive speculative decoding).

• flash_mla_mega_attn –

  DeepSeek V4.1 attention on FlashMLA's mega-attention kernel (SM100).

• flashinfer_sparse –

  DeepSeek V4 FlashInfer sparse MLA backend.

• flashmla –
• model –
• model_state –
• ops –
• vl_model –

  DeepSeek-V4.1 vision variant.