GitLab

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

Fix metax add rms_norm operators.

* ISSUE/628 适配QY C610 GPU，增加编译选项，适配已有算子。添加bge类模型所需的算子，包括gelu,layer_norm，lp_norm(支持l1，l2 norm)，relu，softmax，tanh。

---------
Co-authored-by: xgqdut2016 <kenan_gewei@163.com>
Co-authored-by: xgqdut2016 <140036308+xgqdut2016@users.noreply.github.com>

issue/642 - added a breakpoint in run.py debug

* issue/636 - add support for fp8 with maca sdk

* issue/636 - add functional header to support Fn

* issue/636 - format code with clang

issue/637 - 为from_list函数添加bf16数据类型的支持

issue/608- 修改functional中的rope, 添加nn.RoPE的实现和测试

Co-authored-by: pengcheng888 <pengcheng@example.com>