Skip to content

Request: DFlash draft checkpoint for Qwen3.5-2B/0.8B #100

@AloneGu

Description

@AloneGu

Currently, the only available DFlash draft model is Qwen3.5-4B-DFlash, which is paired with the Qwen3.5-4B target model. However, when deploying on consumer-grade GPUs (e.g., 2× 16GB), the Mamba cache required by the DFlash draft model consumes significant VRAM, making it difficult to use the recommended block_size=16 without running into OOM errors.A smaller DFlash draft checkpoint (e.g., trained from Qwen3.5-2B or Qwen3.5-0.8B) would be highly beneficial for memory-constrained deployments while still enabling speculative decoding acceleration.

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Type

    No type

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions