Skip to content

feat: ensure zero gpu works for Mellea huggingface backend (including for granite switch) #1421

Open

Description

@jakelorocco

Blocked by: #1018

We need to make sure that Mellea works correctly in hugging face's zeroGPU runtime environments. We need to ensure the huggingface implementation of granite-switch in Mellea works as well.

Activity

  1. added
    enhancementNew feature or request
    p1High: important bugs (workaround exists) or high-value core features. Do soon, not on fire.
    on Jul 21, 2026
  2. added theissue type on Jul 21, 2026
  3. added
    area/backendsProvider-specific work: Ollama, HF, LiteLLM, OpenAI, Bedrock, vLLM
    area/adapter-functionsGranite adapter functions: framework and adaptiers including RAG, Guardian, Core
    on Jul 21, 2026
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Metadata

Metadata

Assignees

No one assigned

    Labels

    area/adapter-functionsGranite adapter functions: framework and adaptiers including RAG, Guardian, Corearea/backendsProvider-specific work: Ollama, HF, LiteLLM, OpenAI, Bedrock, vLLMenhancementNew feature or requestp1High: important bugs (workaround exists) or high-value core features. Do soon, not on fire.

    Type

    Projects

    No projects

      Milestone

      No milestone

      Relationships

      None yet

      Development

      No branches or pull requests

      Issue actions