CANN: Simplify the environment variable setting(#13104)

* Simplify the environment variable setting to specify the memory pool type.

* Adjust the GGML_CANN_ASYNC_MODE setting to accept yes, enable, 1, or on (case-insensitive) as valid options.

* update

* fix CI

* update

* delete whitespace

* fix according to review

* update CANN.md

* update CANN.md
This commit is contained in:
Xinpeng Dou 2025-06-09 19:47:39 +08:00 committed by GitHub
parent dc0623fddb
commit e21d2d4ae2
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
3 changed files with 59 additions and 10 deletions

View file

@ -8,6 +8,7 @@
- [DataType Supports](#datatype-supports)
- [Docker](#docker)
- [Linux](#linux)
- [Environment variable setup](#environment-variable-setup)
- [TODO](#todo)
@ -290,5 +291,24 @@ Authors from Peking University: Bizhao Shi (bshi@pku.edu.cn), Yuxin Yang (yxyang
We would like to thank Tuo Dai, Shanni Li, and all of the project maintainers from Huawei Technologies Co., Ltd for their help during the code development and pull request.
## Environment variable setup
### GGML_CANN_ASYNC_MODE
Enables asynchronous operator submission. Disabled by default.
### GGML_CANN_MEM_POOL
Specifies the memory pool management strategy:
- vmm: Utilizes a virtual memory manager pool. If hardware support for VMM is unavailable, falls back to the legacy (leg) memory pool.
- prio: Employs a priority queue-based memory pool management.
- leg: Uses a fixed-size buffer pool.
### GGML_CANN_DISABLE_BUF_POOL_CLEAN
Controls automatic cleanup of the memory pool. This option is only effective when using the prio or leg memory pool strategies.
## TODO
- Support more models and data types.