GitLab

* issue/634: InfiniCore 支持InfiniLM Llama模型适配
Signed-off-by: Ceng23333 <441651826@qq.com>

* .
Signed-off-by: Ceng23333 <441651826@qq.com>

---------
Signed-off-by: Ceng23333 <441651826@qq.com>

issue/679 - 减少创建和使用infini.tensor对象过程中的属性调用次数，以降低耗时

Issue/676 昆仑芯 topkrouter

issue/684: QY机器添加通信库编译选项

* issue/672 - fixed non-contiguous operations in the test framework

issue/680-为mulmat添加alpha参数算子

fix: correct macro for mccub/hccub conditional compilation.

issue/666 - Standardized test imports

issue/612 - differentiate mempcy sync/async

Issue/658 - Update test tolerances and remove device-specific dtype f…

将 `README.md` 中的 `pip install . -e` 改为 `pip install -e .`

Issue/661 - Support run.py --bench

Feature/moore adapt

- Implement Moore backend for add, mul, and silu elementwise operations
- Filter unsupported dtypes (BF16, F64) for Moore platform in tests

issue/656 - updated readme

Issue/648 - Remove metax device support for layer_norm, softmax, and …

Issue/654 - Fix CUDA 13.0 compatibility issues

issue/652- 修改rope函数的测试脚本