vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Update the cann backend News content: Support F16 and F32 data type model for Ascend 310P NPU.

Browse source
This commit is contained in:
leo-pony 2024-11-26 22:07:13 +08:00
parent dc60ede113
commit dc96a0b06a
1 changed files with 3 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

3
docs/backend/CANN.md
View file

@ -23,6 +23,8 @@ The llama.cpp CANN backend is designed to support Ascend NPU. It utilize the abi
## News ## News
- 2024.11
- Support F16 and F32 data type model for Ascend 310P NPU.
- 2024.8 - 2024.8
- Support `Q4_0` and `Q8_0` data type for Ascend NPU. - Support `Q4_0` and `Q8_0` data type for Ascend NPU.
- 2024.7 - 2024.7
@ -43,6 +45,7 @@ The llama.cpp CANN backend is designed to support Ascend NPU. It utilize the abi
| Ascend NPU | Status | | Ascend NPU | Status |
|:-----------------------------:|:-------:| |:-----------------------------:|:-------:|
| Atlas 300T A2 | Support | | Atlas 300T A2 | Support |
| Atlas 300I Duo | Support |
*Notes:* *Notes:*