请教CUPY/CUDA
Open
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 585
- Forks
- 67
- PR merge metrics
- No merged PRs in 30d
Description
- 您好，如图所述，我想查看 cupy操作cuda的函数的具体定义和用法，但是可能是因为cupy封装了c/c++代码，所以看不到，请问可以去哪里看呢？
能帮忙解释一下图中第3个参数 routine 里面 4个函数执行顺序吗（我了解大概是 创建结构体、计算对称量化的scale）
跳到定义处，就只有这样的doc
- 请问下图红框内为什么那样写？
3. 想问一下为什么选择使用cupy直接操作cuda呢，比如allocator、igemm、fgemm的应用？这样相比使用框架（如pytorch等）实现量化有更大的好处吗？感觉cupy+cuda实现方式 要求挺高的
非常感谢
@a710128
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
No file or test is named. Start by locating the CuPy/CUDA call and the routine shown in the attached screenshots, then trace its definitions in the repository and relevant upstream sources. Done would require documenting the routine's function order, the highlighted syntax, and the rationale for using CuPy with CUDA instead of a framework.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- machine-learning
- Issue type
- Documentation
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100