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

ggml-webgpu: Add unary op (SQR, SQRT, SIN, COS) support. (#19700)

Browse source 
* ggml-webgpu: Add unary op (SQR, SQRT, SIN, COS) support.

* Fix to cast the src value to f32 before sin/cos computing.
This commit is contained in:
Masashi Yoshimura 2026-02-20 01:18:30 +09:00 • committed by GitHub
parent 237958db33
commit 11c325c6e0
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
4 changed files with 62 additions and 20 deletions
Download patch file Download diff file Expand all files Collapse all files

40
docs/ops/WebGPU.csv
View file

@ -8760,22 +8760,14 @@
"WebGPU: WebGPU","ADD_ID","type_a=f32,type_b=f32,n_embd=129,n_experts=8,n_experts_used=4,n_token=1","support","0","no","WebGPU"
"WebGPU: WebGPU","ADD_ID","type_a=f32,type_b=f32,n_embd=129,n_experts=8,n_experts_used=4,n_token=32","support","0","no","WebGPU"
"WebGPU: WebGPU","ADD_ID","type_a=f32,type_b=f32,n_embd=129,n_experts=8,n_experts_used=4,n_token=129","support","0","no","WebGPU"
"WebGPU: WebGPU","SQR","type=f16,ne=[10,5,4,3]","support","0","no","WebGPU"
"WebGPU: WebGPU","SQRT","type=f16,ne=[10,3,3,2]","support","0","no","WebGPU"
"WebGPU: WebGPU","LOG","type=f16,ne=[10,5,4,3]","support","1","yes","WebGPU"
"WebGPU: WebGPU","SIN","type=f16,ne=[10,2,2,2]","support","0","no","WebGPU"
"WebGPU: WebGPU","COS","type=f16,ne=[10,2,2,2]","support","0","no","WebGPU"
"WebGPU: WebGPU","CLAMP","type=f16,ne=[10,5,4,3],min=-0.500000,max=0.500000","support","1","yes","WebGPU"
"WebGPU: WebGPU","LEAKY_RELU","type=f16,ne_a=[10,5,4,3],negative_slope=0.100000","support","0","no","WebGPU"
"WebGPU: WebGPU","FLOOR","type=f16,ne=[10,2,2,2]","support","1","yes","WebGPU"
"WebGPU: WebGPU","CEIL","type=f16,ne=[10,2,2,2]","support","1","yes","WebGPU"
"WebGPU: WebGPU","ROUND","type=f16,ne=[10,2,2,2]","support","1","yes","WebGPU"
"WebGPU: WebGPU","TRUNC","type=f16,ne=[10,2,2,2]","support","1","yes","WebGPU"
"WebGPU: WebGPU","SQR","type=f16,ne=[7,1,5,3]","support","0","no","WebGPU"
"WebGPU: WebGPU","SQRT","type=f16,ne=[7,1,5,3]","support","0","no","WebGPU"
"WebGPU: WebGPU","LOG","type=f16,ne=[7,1,5,3]","support","1","yes","WebGPU"
"WebGPU: WebGPU","SIN","type=f16,ne=[7,1,5,3]","support","0","no","WebGPU"
"WebGPU: WebGPU","COS","type=f16,ne=[7,1,5,3]","support","0","no","WebGPU"
"WebGPU: WebGPU","CLAMP","type=f16,ne=[7,1,5,3],min=-0.500000,max=0.500000","support","1","yes","WebGPU"
"WebGPU: WebGPU","LEAKY_RELU","type=f16,ne_a=[7,1,5,3],negative_slope=0.100000","support","0","no","WebGPU"
"WebGPU: WebGPU","FLOOR","type=f16,ne=[7,1,5,3]","support","1","yes","WebGPU"
@ -8786,22 +8778,14 @@
"WebGPU: WebGPU","ROUND","type=f16,ne=[1024,1024,1,1]","support","1","yes","WebGPU"
"WebGPU: WebGPU","TRUNC","type=f16,ne=[7,1,5,3]","support","1","yes","WebGPU"
"WebGPU: WebGPU","TRUNC","type=f16,ne=[1024,1024,1,1]","support","1","yes","WebGPU"
"WebGPU: WebGPU","SQR","type=f32,ne=[10,5,4,3]","support","0","no","WebGPU"
"WebGPU: WebGPU","SQRT","type=f32,ne=[10,3,3,2]","support","0","no","WebGPU"
"WebGPU: WebGPU","LOG","type=f32,ne=[10,5,4,3]","support","1","yes","WebGPU"
"WebGPU: WebGPU","SIN","type=f32,ne=[10,2,2,2]","support","0","no","WebGPU"
"WebGPU: WebGPU","COS","type=f32,ne=[10,2,2,2]","support","0","no","WebGPU"
"WebGPU: WebGPU","CLAMP","type=f32,ne=[10,5,4,3],min=-0.500000,max=0.500000","support","1","yes","WebGPU"
"WebGPU: WebGPU","LEAKY_RELU","type=f32,ne_a=[10,5,4,3],negative_slope=0.100000","support","0","no","WebGPU"
"WebGPU: WebGPU","FLOOR","type=f32,ne=[10,2,2,2]","support","1","yes","WebGPU"
"WebGPU: WebGPU","CEIL","type=f32,ne=[10,2,2,2]","support","1","yes","WebGPU"
"WebGPU: WebGPU","ROUND","type=f32,ne=[10,2,2,2]","support","1","yes","WebGPU"
"WebGPU: WebGPU","TRUNC","type=f32,ne=[10,2,2,2]","support","1","yes","WebGPU"
"WebGPU: WebGPU","SQR","type=f32,ne=[7,1,5,3]","support","0","no","WebGPU"
"WebGPU: WebGPU","SQRT","type=f32,ne=[7,1,5,3]","support","0","no","WebGPU"
"WebGPU: WebGPU","LOG","type=f32,ne=[7,1,5,3]","support","1","yes","WebGPU"
"WebGPU: WebGPU","SIN","type=f32,ne=[7,1,5,3]","support","0","no","WebGPU"
"WebGPU: WebGPU","COS","type=f32,ne=[7,1,5,3]","support","0","no","WebGPU"
"WebGPU: WebGPU","CLAMP","type=f32,ne=[7,1,5,3],min=-0.500000,max=0.500000","support","1","yes","WebGPU"
"WebGPU: WebGPU","LEAKY_RELU","type=f32,ne_a=[7,1,5,3],negative_slope=0.100000","support","0","no","WebGPU"
"WebGPU: WebGPU","FLOOR","type=f32,ne=[7,1,5,3]","support","1","yes","WebGPU"
@ -18901,3 +18885,27 @@
"WebGPU: WebGPU","CROSS_ENTROPY_LOSS_BACK","type=f32,ne=[30000,1,1,1]","support","0","no","WebGPU"
"WebGPU: WebGPU","OPT_STEP_ADAMW","type=f32,ne=[10,5,4,3]","support","0","no","WebGPU"
"WebGPU: WebGPU","OPT_STEP_SGD","type=f32,ne=[10,5,4,3]","support","0","no","WebGPU"
"WebGPU: WebGPU","SQR","type=f16,ne=[10,5,4,3]","support","1","yes","WebGPU"
"WebGPU: WebGPU","SQRT","type=f16,ne=[10,3,3,2]","support","1","yes","WebGPU"
"WebGPU: WebGPU","SIN","type=f16,ne=[10,2,2,2]","support","1","yes","WebGPU"
"WebGPU: WebGPU","COS","type=f16,ne=[10,2,2,2]","support","1","yes","WebGPU"
"WebGPU: WebGPU","SQR","type=f16,ne=[7,1,5,3]","support","1","yes","WebGPU"
"WebGPU: WebGPU","SQR","type=f16,ne=[1024,1024,1,1]","support","1","yes","WebGPU"
"WebGPU: WebGPU","SQRT","type=f16,ne=[7,1,5,3]","support","1","yes","WebGPU"
"WebGPU: WebGPU","SQRT","type=f16,ne=[1024,1024,1,1]","support","1","yes","WebGPU"
"WebGPU: WebGPU","SIN","type=f16,ne=[7,1,5,3]","support","1","yes","WebGPU"
"WebGPU: WebGPU","SIN","type=f16,ne=[1024,1024,1,1]","support","1","yes","WebGPU"
"WebGPU: WebGPU","COS","type=f16,ne=[7,1,5,3]","support","1","yes","WebGPU"
"WebGPU: WebGPU","COS","type=f16,ne=[1024,1024,1,1]","support","1","yes","WebGPU"
"WebGPU: WebGPU","SQR","type=f32,ne=[10,5,4,3]","support","1","yes","WebGPU"
"WebGPU: WebGPU","SQRT","type=f32,ne=[10,3,3,2]","support","1","yes","WebGPU"
"WebGPU: WebGPU","SIN","type=f32,ne=[10,2,2,2]","support","1","yes","WebGPU"
"WebGPU: WebGPU","COS","type=f32,ne=[10,2,2,2]","support","1","yes","WebGPU"
"WebGPU: WebGPU","SQR","type=f32,ne=[7,1,5,3]","support","1","yes","WebGPU"
"WebGPU: WebGPU","SQR","type=f32,ne=[1024,1024,1,1]","support","1","yes","WebGPU"
"WebGPU: WebGPU","SQRT","type=f32,ne=[7,1,5,3]","support","1","yes","WebGPU"
"WebGPU: WebGPU","SQRT","type=f32,ne=[1024,1024,1,1]","support","1","yes","WebGPU"
"WebGPU: WebGPU","SIN","type=f32,ne=[7,1,5,3]","support","1","yes","WebGPU"
"WebGPU: WebGPU","SIN","type=f32,ne=[1024,1024,1,1]","support","1","yes","WebGPU"
"WebGPU: WebGPU","COS","type=f32,ne=[7,1,5,3]","support","1","yes","WebGPU"
"WebGPU: WebGPU","COS","type=f32,ne=[1024,1024,1,1]","support","1","yes","WebGPU"

Can't render this file because it is too large.