Awesome-LLM-Inference

GitHub

📚A curated list of Awesome LLM/VLM Inference Papers with Codes: Flash-Attention, Paged-Attention, WINT8/4, Parallelism, etc.🎉

5,350 stars Python 1 file · ~21,105 tokens #awesome-llm #deepseek #deepseek-r1 #deepseek-v3 #flash-attention #flash-attention-3 #flash-mla #llm-inference

Awesome-LLM-Inference MCP Server

MCP server for xlite-dev/Awesome-LLM-Inference

Ready-to-Use Client Configurations

{
  "mcpServers": {
    "Awesome-LLM-Inference": {
      "command": "npx",
      "args": [
        "-y",
        "@xlite-dev/Awesome-LLM-Inference"
      ]
    }
  }
}

{
  "mcpServers": {
    "Awesome-LLM-Inference": {
      "command": "npx",
      "args": [
        "-y",
        "@xlite-dev/Awesome-LLM-Inference"
      ]
    }
  }
}

{
  "mcpServers": {
    "Awesome-LLM-Inference": {
      "command": "npx",
      "args": [
        "-y",
        "@xlite-dev/Awesome-LLM-Inference"
      ]
    }
  }
}

{
  "mcpServers": {
    "Awesome-LLM-Inference": {
      "command": "npx",
      "args": [
        "-y",
        "@xlite-dev/Awesome-LLM-Inference"
      ],
      "disabled": false,
      "autoApprove": []
    }
  }
}

{
  "mcpServers": {
    "Awesome-LLM-Inference": {
      "command": "npx",
      "args": [
        "-y",
        "@xlite-dev/Awesome-LLM-Inference"
      ]
    }
  }
}

docker run -i --rm mcp/Awesome-LLM-Inference