Skip to main content

sageLLM backend provider abstraction (CPU/CUDA/Ascend)

Project description

sagellm-backend

Protocol Compliance (Mandatory)

CI PyPI version Python Version License Code style: ruff

硬件抽象层 - 为 sageLLM 提供统一的硬件接口(CUDA/Ascend/Kunlun)

架构定位

┌─────────────────────────────────────────────────────────────┐
│  sagellm-core (引擎协调层)                                   │
│  • BaseEngine, EngineFactory                               │
│  • CPUEngine, HFCudaEngine                                 │
├─────────────────────────────────────────────────────────────┤
│  sagellm-backend (硬件抽象层) ← 本仓库                       │
│  ┌─────────────────────────────────────────────────────┐    │
│  │  BackendProvider Interface                         │    │
│  │  • Stream/Event 异步流                              │    │
│  │  • KVBlock 内存管理                                 │    │
│  │  • Collective 操作(all_reduce/all_gather)        │    │
│  └─────────────────────────────────────────────────────┘    │
│  ┌──────────┐  ┌──────────┐  ┌──────────┐                  │
│  │  CUDA    │  │  Ascend  │  │  Kunlun  │                  │
│  │ Provider │  │ Provider │  │ Provider │                  │
│  └──────────┘  └──────────┘  └──────────┘                  │
├─────────────────────────────────────────────────────────────┤
│  Hardware SDK Layer                                          │
│  CUDA/cuDNN/NCCL │ CANN/HCCL │ XPU SDK │ DCU SDK           │
└─────────────────────────────────────────────────────────────┘

职责分离(v0.2.0 重构)

  • 本仓库负责:硬件抽象、设备管理、内存原语
  • 不再包含:BaseEngine, EngineFactory(已移至 sagellm-core)
  • 🔗 被使用于:sagellm-core 中的引擎实现

Features

  • 统一硬件抽象:单一 API 支持多硬件后端
  • CPU Backend:无 GPU 环境的默认后端
  • CUDA Support:原生 CUDA 后端实现
  • CPU Support:CPU-only 后端实现
  • 能力发现:硬件能力查询与验证

Installation

pip install isagellm-backend

Quick Start

git clone git@github.com:intellistream/sagellm-backend.git
cd sagellm-backend
./quickstart.sh

# Run tests
pytest tests/ -v

Usage Examples

Basic Backend Usage

from sagellm_backend import CPUBackendProvider, DType

# Create backend
backend = CPUBackendProvider()

# Query capabilities
cap = backend.capability()
print(cap.supported_dtypes)

# Allocate KV block
block = backend.kv_block_alloc(128, DType.FP16)

Using with sagellm-core Engines

注意:引擎实现(如 HFCudaEngine)已移至 sagellm-core。Backend 现在专注于硬件抽象。

# 引擎现在位于 sagellm-core
from sagellm_core import HFCudaEngine, EngineFactory
from sagellm_backend import CPUBackendProvider

# 创建 backend
backend = CPUBackendProvider()

# 使用 EngineFactory(来自 core)
engine = EngineFactory.create(
    backend_type="cpu",
    config={
        "engine_id": "cpu-001",
        "model_path": "TinyLlama/TinyLlama-1.1B-Chat-v1.0",
    },
    provider=backend,
)

Extending with New Backends

# Create provider in providers/ directory
class AscendBackendProvider:
    def capability(self) -> CapabilityDescriptor:
        return CapabilityDescriptor(
            supported_dtypes=[DType.FP16, DType.BF16, DType.INT8],
            # ...
        )

    # Implement other interface methods...

# Register via entry point in pyproject.toml
[project.entry-points."sagellm.backends"]
ascend_cann = "sagellm_backend.providers.ascend:create_ascend_backend"

Documentation

License

Proprietary

Project details


Release history Release notifications | RSS feed

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

isagellm_backend-0.3.0.10.tar.gz (97.0 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

isagellm_backend-0.3.0.10-py2.py3-none-any.whl (126.9 kB view details)

Uploaded Python 2Python 3

File details

Details for the file isagellm_backend-0.3.0.10.tar.gz.

File metadata

  • Download URL: isagellm_backend-0.3.0.10.tar.gz
  • Upload date:
  • Size: 97.0 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.11.14

File hashes

Hashes for isagellm_backend-0.3.0.10.tar.gz
Algorithm Hash digest
SHA256 eeac150c1d6918f918d038c76b3242142963000364dd15254f0f170817c0d89f
MD5 8fe8daea46d3ae353bd6a8b8ac560970
BLAKE2b-256 9316068b631df9f807c471d99b4752d0fee4d30fe6e9825f5c61622085e67368

See more details on using hashes here.

File details

Details for the file isagellm_backend-0.3.0.10-py2.py3-none-any.whl.

File metadata

File hashes

Hashes for isagellm_backend-0.3.0.10-py2.py3-none-any.whl
Algorithm Hash digest
SHA256 f3ea777c9e53e7dc340596c7b990d0cb65cb120890062687493fafcb0270ff4f
MD5 ab94e2b6f6ee40905f8fa3e55ac8ec3a
BLAKE2b-256 ca478590d1f34e63845fd3d6a86f8417972ec3c30c1ebc1a07b7b91983238c25

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page