Hugging Face's logo

aws-neuron
/
optimum-neuron-cache

Model card Files
xet
 Community
711
optimum-neuron-cache / inference-cache-config

Commit History

  1. Update inference-cache-config/trn1/mixtral.json

    dacorvo HF Staff
    Verified signature
    8343560

  2. Update inference-cache-config/trn1/mixtral.json

    dacorvo HF Staff
    Verified signature
    e64396b

  1. clean-up Trainium 1 cached configurations

    dacorvo HF Staff
    3263dce

  2. add trn2 cached configs subdirectory

    dacorvo HF Staff
    25e9ebd

  3. Delete inference-cache-config/mistral.json

    dacorvo HF Staff
    Verified signature
    cdc796b

  4. Delete inference-cache-config/mistral-variants.json

    dacorvo HF Staff
    Verified signature
    3551ea0

  5. Delete inference-cache-config/gpt2.json

    dacorvo HF Staff
    Verified signature
    26418d4

  1. Update inference-cache-config/llama-variants.json

    dacorvo HF Staff
    Verified signature
    a510ca8

  1. Update inference-cache-config/llama4.json

    dacorvo HF Staff
    Verified signature
    711bb96

  1. Update inference-cache-config/smollm3.json

    dacorvo HF Staff
    Verified signature
    5c18776

  2. Update inference-cache-config/smollm3.json

    dacorvo HF Staff
    Verified signature
    fd79a3f

  1. Update inference-cache-config/qwen-moe.json

    dacorvo HF Staff
    Verified signature
    51619c0

  1. Update inference-cache-config/qwen-moe.json

    dacorvo HF Staff
    Verified signature
    6266253

  1. Create llama4.json

    dacorvo HF Staff
    Verified signature
    05a6e8d

  1. Rename inference-cache-config/qwen3-moe.json to inference-cache-config/qwen-moe.json

    dacorvo HF Staff
    Verified signature
    24ae643

  1. Update inference-cache-config/qwen3-moe.json

    dacorvo HF Staff
    Verified signature
    5e828c9

  2. add cached qwen3-moe configurations

    dacorvo HF Staff
    Verified signature
    2fdfa36

  1. Update inference-cache-config/smollm3.json

    dacorvo HF Staff
    Verified signature
    aa1b2eb

  2. Update inference-cache-config/smollm3.json

    dacorvo HF Staff
    Verified signature
    8a334d7

  3. Update inference-cache-config/smollm3.json

    dacorvo HF Staff
    Verified signature
    28ae1e4

  4. Add smollm3 model configurations

    dacorvo HF Staff
    Verified signature
    b76c1a7

  1. Update inference-cache-config/llama.json

    dacorvo HF Staff
    Verified signature
    325c041

  1. Update inference-cache-config/qwen.json

    dacorvo HF Staff
    Verified signature
    8d1681e

  2. Create qwen.json

    dacorvo HF Staff
    Verified signature
    a166114

  1. Add batch size 4 configurations for LLama 1B and 3B models

    dacorvo HF Staff
    Verified signature
    3b6312a

  1. Rename inference-cache-config/pixart_sigma_xl_512x512.json to inference-cache-config/pixart-sigma-xl-512x512.json

    Jingya HF Staff
    Verified signature
    1d662ce

  2. Create pixart_sigma_xl_512x512.json

    Jingya HF Staff
    Verified signature
    13f78a6

  3. Rename inference-cache-config/pixart-xl-2-512x512.json to inference-cache-config/pixart-alpha-xl-512x512.json

    Jingya HF Staff
    Verified signature
    cb11624

  4. Rename inference-cache-config/pixArt-XL-2-512x512.json to inference-cache-config/pixart-xl-2-512x512.json

    Jingya HF Staff
    Verified signature
    c7f992d

  5. Create pixArt-XL-2-512x512.json

    Jingya HF Staff
    Verified signature
    600ade6

  6. Create sdxl-turbo.json

    Jingya HF Staff
    Verified signature
    591ea52

  7. Create stable-diffusion-xl-refiner-1.0.json

    Jingya HF Staff
    Verified signature
    aa72a1a

  8. Create stable-diffusion-xl-base-1.0.json

    Jingya HF Staff
    Verified signature
    1554744

  9. Create stable-diffusion-2-1.json

    Jingya HF Staff
    Verified signature
    e4e1333

  10. Rename inference-cache-config/diffusion.json to inference-cache-config/stable-diffusion-v1-5.json

    Jingya HF Staff
    Verified signature
    4a034bb

  1. add pixart and remove deprecated

    Jingya HF Staff
    Verified signature
    e5f06c7

  1. Added TinyLlama as requested by Jim burtoft

    dacorvo HF Staff
    Verified signature
    d9640f4

  1. Add phi4 cached configurations

    dacorvo HF Staff
    Verified signature
    c564534

  1. Add DeepSeek distilled versions of LLama 8B

    dacorvo HF Staff
    Verified signature
    509e6bf

  2. Add DeepSeek distilled model

    dacorvo HF Staff
    Verified signature
    4d1e615

  1. Update inference-cache-config/qwen2.5-large.json

    dacorvo HF Staff
    Verified signature
    84982b8

  2. Add DeepSeek distilled models

    dacorvo HF Staff
    Verified signature
    f4f3dcd

  1. Update inference-cache-config/mistral.json

    dacorvo HF Staff
    Verified signature
    01e1fe9

  2. Update inference-cache-config/mistral.json

    dacorvo HF Staff
    Verified signature
    7191bac

  1. Update inference-cache-config/mistral.json

    dacorvo HF Staff
    Verified signature
    6b536dc

  1. Add configuration for granite models

    dacorvo HF Staff
    Verified signature
    687da09

  1. Rename inference-cache-config/qwen-2.5-large.json to inference-cache-config/qwen2.5-large.json

    dacorvo HF Staff
    Verified signature
    2aa52ac

  2. Create qwen-2.5-large.json

    dacorvo HF Staff
    Verified signature
    a8df9db

  3. Rename inference-cache-config/qwen2.5 to inference-cache-config/qwen2.5.json

    dacorvo HF Staff
    Verified signature
    b9f1fde

  4. Add qwen2.5 config for models up to 14B params

    dacorvo HF Staff
    Verified signature
    4e25bb0