Skip to content

vllm.models.deepseek_v41.nvidia

Modules:

  • dspark –

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

  • engram –

    NVIDIA Engram DP sharding, shared host storage, and asynchronous prefetch.

  • 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.