thek0tyara/llama-cpp-turboquant
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions 6

Updated readme description

Browse source
This commit is contained in:
Alejandro Saucedo 2020-08-23 06:50:52 +01:00
parent d0a1f5f5ed
commit 362368c712
1 changed files with 2 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

3
README.md
View file

@ -2,6 +2,7 @@
## Principles
* Single header easy to import library to boost your Vulkan compute experience
* Non-vulkan naming convention to disambiguate Vulkan vs Kompute components
* Extends the existing vulkan API with a simpler compute-specific interface
* BYOV: Play nice with existing Vulkan applications with a bring-your-own-Vulkan design
@ -46,7 +47,7 @@ int main() {
// Begin recoding commands
sq.begin();
// Run batch operations to be sent to GPU
// Record sequence of operations to be sent to GPU in batch
{
sq.record<kp::OpCreateTensor>({ tensorLHS });
sq.record<kp::OpCreateTensor>({ tensorRHS });