Blog-explorers

llama-server -hf unsloth/Devstral-Small-2505-GGUF:Q4_K_M

name: Llama.cpp model
    version: 0.0.1
    schema: v1
    models:
      - provider: llama.cpp
        model: unsloth/Devstral-Small-2505-GGUF
        apiBase: http://localhost:8080
        defaultCompletionOptions:
          contextLength: 8192 
    # Adjust based on the model
        name: Llama.cpp Devstral-Small
        roles:
          - chat
          - edit

name: Playwright mcpServer
    version: 0.0.1
    schema: v1
    mcpServers:
      - name: Browser search
        command: npx
        args:
          - "@playwright/mcp@latest"

import spaces
from diffusers import FluxPipeline
from torchao.quantization.quant_api import Int8WeightOnlyConfig, quantize_

pipeline = FluxPipeline.from_pretrained(...).to('cuda')
quantize_(pipeline.transformer, Int8WeightOnlyConfig()) # Or any other component(s)

@spaces.GPU
def generate(prompt: str):
    return pipeline(prompt).images[0]