Star680
378
代码介绍
代码
Issues26
Pull Requests43
流水线
Actions
讨论
Wiki
项目成员245
分析
项目设置
Star680
378
  1. cann-recipes-infer
  2. /
  3. executor
  4. /
  5. online
cann-robotcann-robot【feat】feat multi block_size in cache management
48a59dc0创建于 3 天前历史提交
文件最后提交记录最后更新时间
kv_transfer
【feat】feat multi block_size in cache management3 天前
scheduler
【feat】feat multi block_size in cache management3 天前
__init__.py
refactor: 支持online多batch推理1 个月前
bootstrap.py
【feat】feat multi block_size in cache management3 天前
constants.py
refactor: 支持online多batch推理1 个月前
dp_dispatcher.py
refactor: 支持online多batch推理1 个月前
online_inference.py
[docs] add framwork checklist26 天前
requirements.txt
[refactor]修改online依赖CPU通信域初始化流程1 个月前
router.py
refactor: 支持online多batch推理1 个月前
server.py
[feat] mooncake + hixl, import, support models lazy import27 天前