ggerganov commited on
Commit
d1fa03c
·
unverified ·
1 Parent(s): 9a2f912

update : readme

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -16,7 +16,7 @@ High-performance inference of [OpenAI's Whisper](https://github.com/openai/whisp
16
  - AVX intrinsics support for x86 architectures
17
  - VSX intrinsics support for POWER architectures
18
  - Mixed F16 / F32 precision
19
- - [4-bit and 5-bit integer quantization support](#quantization)
20
  - Zero memory allocations at runtime
21
  - [Vulkan support](#vulkan-gpu-support)
22
  - Support for CPU-only inference
 
16
  - AVX intrinsics support for x86 architectures
17
  - VSX intrinsics support for POWER architectures
18
  - Mixed F16 / F32 precision
19
+ - [Integer quantization support](#quantization)
20
  - Zero memory allocations at runtime
21
  - [Vulkan support](#vulkan-gpu-support)
22
  - Support for CPU-only inference