thek0tyara/llama-cpp-turboquant
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions 4

Updated readme

Browse source
This commit is contained in:
Alejandro Saucedo 2020-10-18 06:57:46 +01:00
parent eb6aaa8039
commit 7e5a47bf23
1 changed files with 2 additions and 2 deletions
Download patch file Download diff file Expand all files Collapse all files

4
README.md
View file

@ -57,7 +57,7 @@ In this simple example we will:
3. Define shader as string or spirv bytes (can also pass path to file) 3. Define shader as string or spirv bytes (can also pass path to file)
4. Run compute shader asynchronously with Async function 4. Run compute shader asynchronously with Async function
5. Create managed sequence to submit batch operations to the CPU 5. Create managed sequence to submit batch operations to the CPU
6. Map data back to host using the sequence showing batch operations 6. Map data back to host by running the sequence of batch operations
View [more examples](https://kompute.cc/overview/advanced-examples.html#simple-examples). View [more examples](https://kompute.cc/overview/advanced-examples.html#simple-examples).
@ -111,7 +111,7 @@ int main() {
// Before submitting sequence batch we wait for the previous async operation // Before submitting sequence batch we wait for the previous async operation
mgr.evalOpAwaitDefault(); mgr.evalOpAwaitDefault();
// 6. Map data back to host using the sequence showing batch operations // 6. Map data back to host by running the sequence of batch operations
sq->eval(); sq->eval();
// Prints the output which is A: { 0, 1, 2 } B: { 3, 4, 5 } // Prints the output which is A: { 0, 1, 2 } B: { 3, 4, 5 }