abetlen / abetlen/llama-cpp-python
Have you thought about adding quantum cache or 8 bit cache?
Đang mở
enhancement
- Ngôn ngữ chính
- Python
- Star
- 10.6k
- Fork
- 1.4k
- Chỉ số merge pull request
- Chỉ số pull request đang chờ
Mô tả
I've figured out how to change the type. It's a little slower but it does save memory.
The numbers for type_K or V simply correspond to the cache types in ggml.h
```
GGML_TYPE_F32 = 0,
GGML_TYPE_F16 = 1,
GGML_TYPE_Q4_0 = 2,
GGML_TYPE_Q4_1 = 3,
// GGML_TYPE_Q4_2 = 4, support has been removed
// GGML_TYPE_Q4_3 (5) support has been removed
GGML_TYPE_Q5_0 = 6,
GGML_TYPE_Q5_1 = 7,
GGML_TYPE_Q8_0 = 8,
GGML_TYPE_Q8_1 = 9,
```
Hướng dẫn đóng góp
Đánh giá
Issue này chưa được đánh giá.