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

Added the raedme exampel

Browse source
This commit is contained in:
Alejandro Saucedo 2021-03-05 08:35:21 +00:00
parent 33a0ef933b
commit d26ef2738d
1 changed files with 4 additions and 2 deletions
Download patch file Download diff file Expand all files Collapse all files

6
README.md
View file

@ -78,8 +78,9 @@ void kompute(const std::string& shader) {
mgr.sequence()
->record<kp::OpTensorSyncDevice>(params)
->record<kp::OpAlgoDispatch>(algorithm) // Binds default push consts
->eval() // Evaluates the two recorded operations
->record<kp::OpAlgoDispatch>(algorithm, pushConstsB) // Overrides push consts
->eval();
->eval(); // Evaluates only last recorded operation
// 5. Sync results from the GPU asynchronously
sq = mgr.sequence()
@ -164,8 +165,9 @@ def kompute(shader):
(mgr.sequence()
.record(kp.OpTensorSyncDevice(params))
.record(kp.OpAlgoDispatch(algo)) # Binds default push consts provided
.eval() # evaluates the two recorded ops
.record(kp.OpAlgoDispatch(algo, push_consts_b)) # Overrides push consts
.eval())
.eval()) # evaluates only the last recorded op
# 5. Sync results from the GPU asynchronously
sq = mgr.sequence()