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

ggml-webgpu: Update the RMS_NORM preprocessor and add L2_NORM (#20665)

Browse source 
* Update the preprocessor of RMS_NORM and add L2_NORM.

* Fix the name of rms_norm to row_norm.
This commit is contained in:
Masashi Yoshimura 2026-03-19 13:08:59 +09:00 • committed by GitHub
parent ea01d196d7
commit 509a31d00f
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
5 changed files with 113 additions and 69 deletions
Download patch file Download diff file Expand all files Collapse all files

2
docs/ops.md
View file

@ -62,7 +62,7 @@ Legend:
| HARDSWISH | ❌ | ✅ | ✅ | 🟡 | 🟡 | ❌ | ✅ | 🟡 | ✅ | ❌ | ❌ |
| IM2COL | ❌ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ❌ | ❌ | ❌ |
| IM2COL_3D | ❌ | ❌ | ✅ | ✅ | ❌ | ❌ | ❌ | ✅ | ❌ | ❌ | ❌ |
| L2_NORM | ❌ | ✅ | ✅ | ✅ | ✅ | ❌ | ✅ | ✅ | ❌ | ❌ | ❌ |
| L2_NORM | ❌ | ✅ | ✅ | ✅ | ✅ | ❌ | ✅ | ✅ | ✅ | ❌ | ❌ |
| LEAKY_RELU | ❌ | ✅ | ✅ | ✅ | 🟡 | ❌ | ✅ | 🟡 | ❌ | ❌ | ❌ |
| LOG | ❌ | ✅ | ✅ | ✅ | 🟡 | ❌ | 🟡 | ✅ | ✅ | ❌ | ❌ |
| MEAN | ❌ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ❌ | ❌ | ❌ |

28
docs/ops/WebGPU.csv
View file

@ -5744,49 +5744,61 @@
"WebGPU: WebGPU","NORM","type=f32,ne=[64,5,4,3],v=1,eps=0.000000","support","0","no","WebGPU"
"WebGPU: WebGPU","RMS_NORM","type=f32,ne=[64,5,4,3],v=1,eps=0.000000,inplace=0","support","1","yes","WebGPU"
"WebGPU: WebGPU","RMS_NORM_BACK","type=f32,ne=[64,5,4,3],eps=0.000000","support","0","no","WebGPU"
"WebGPU: WebGPU","L2_NORM","type=f32,ne=[64,5,4,3]","support","0","no","WebGPU"
"WebGPU: WebGPU","L2_NORM","type=f32,ne=[64,5,4,3],eps=0.000000,v=0","support","1","yes","WebGPU"
"WebGPU: WebGPU","L2_NORM","type=f32,ne=[64,5,4,3],eps=0.000000,v=1","support","1","yes","WebGPU"
"WebGPU: WebGPU","NORM","type=f32,ne=[1025,5,4,3],v=0,eps=0.000000","support","0","no","WebGPU"
"WebGPU: WebGPU","RMS_NORM","type=f32,ne=[1025,5,4,3],v=0,eps=0.000000,inplace=0","support","1","yes","WebGPU"
"WebGPU: WebGPU","NORM","type=f32,ne=[1025,5,4,3],v=1,eps=0.000000","support","0","no","WebGPU"
"WebGPU: WebGPU","RMS_NORM","type=f32,ne=[1025,5,4,3],v=1,eps=0.000000,inplace=0","support","1","yes","WebGPU"
"WebGPU: WebGPU","RMS_NORM_BACK","type=f32,ne=[1025,5,4,3],eps=0.000000","support","0","no","WebGPU"
"WebGPU: WebGPU","L2_NORM","type=f32,ne=[1025,5,4,3]","support","0","no","WebGPU"
"WebGPU: WebGPU","L2_NORM","type=f32,ne=[1025,5,4,3],eps=0.000000,v=0","support","1","yes","WebGPU"
"WebGPU: WebGPU","L2_NORM","type=f32,ne=[1025,5,4,3],eps=0.000000,v=1","support","1","yes","WebGPU"
"WebGPU: WebGPU","NORM","type=f32,ne=[64,5,4,3],v=0,eps=0.000001","support","0","no","WebGPU"
"WebGPU: WebGPU","RMS_NORM","type=f32,ne=[64,5,4,3],v=0,eps=0.000001,inplace=0","support","1","yes","WebGPU"
"WebGPU: WebGPU","NORM","type=f32,ne=[64,5,4,3],v=1,eps=0.000001","support","0","no","WebGPU"
"WebGPU: WebGPU","RMS_NORM","type=f32,ne=[64,5,4,3],v=1,eps=0.000001,inplace=0","support","1","yes","WebGPU"
"WebGPU: WebGPU","RMS_NORM_BACK","type=f32,ne=[64,5,4,3],eps=0.000001","support","0","no","WebGPU"
"WebGPU: WebGPU","L2_NORM","type=f32,ne=[64,5,4,3]","support","0","no","WebGPU"
"WebGPU: WebGPU","L2_NORM","type=f32,ne=[64,5,4,3],eps=0.000001,v=0","support","1","yes","WebGPU"
"WebGPU: WebGPU","L2_NORM","type=f32,ne=[64,5,4,3],eps=0.000001,v=1","support","1","yes","WebGPU"
"WebGPU: WebGPU","NORM","type=f32,ne=[1025,5,4,3],v=0,eps=0.000001","support","0","no","WebGPU"
"WebGPU: WebGPU","RMS_NORM","type=f32,ne=[1025,5,4,3],v=0,eps=0.000001,inplace=0","support","1","yes","WebGPU"
"WebGPU: WebGPU","NORM","type=f32,ne=[1025,5,4,3],v=1,eps=0.000001","support","0","no","WebGPU"
"WebGPU: WebGPU","RMS_NORM","type=f32,ne=[1025,5,4,3],v=1,eps=0.000001,inplace=0","support","1","yes","WebGPU"
"WebGPU: WebGPU","RMS_NORM_BACK","type=f32,ne=[1025,5,4,3],eps=0.000001","support","0","no","WebGPU"
"WebGPU: WebGPU","L2_NORM","type=f32,ne=[1025,5,4,3]","support","0","no","WebGPU"
"WebGPU: WebGPU","L2_NORM","type=f32,ne=[1025,5,4,3],eps=0.000001,v=0","support","1","yes","WebGPU"
"WebGPU: WebGPU","L2_NORM","type=f32,ne=[1025,5,4,3],eps=0.000001,v=1","support","1","yes","WebGPU"
"WebGPU: WebGPU","NORM","type=f32,ne=[64,5,4,3],v=0,eps=0.000100","support","0","no","WebGPU"
"WebGPU: WebGPU","RMS_NORM","type=f32,ne=[64,5,4,3],v=0,eps=0.000100,inplace=0","support","1","yes","WebGPU"
"WebGPU: WebGPU","NORM","type=f32,ne=[64,5,4,3],v=1,eps=0.000100","support","0","no","WebGPU"
"WebGPU: WebGPU","RMS_NORM","type=f32,ne=[64,5,4,3],v=1,eps=0.000100,inplace=0","support","1","yes","WebGPU"
"WebGPU: WebGPU","RMS_NORM_BACK","type=f32,ne=[64,5,4,3],eps=0.000100","support","0","no","WebGPU"
"WebGPU: WebGPU","L2_NORM","type=f32,ne=[64,5,4,3]","support","0","no","WebGPU"
"WebGPU: WebGPU","L2_NORM","type=f32,ne=[64,5,4,3],eps=0.000100,v=0","support","1","yes","WebGPU"
"WebGPU: WebGPU","L2_NORM","type=f32,ne=[64,5,4,3],eps=0.000100,v=1","support","1","yes","WebGPU"
"WebGPU: WebGPU","NORM","type=f32,ne=[1025,5,4,3],v=0,eps=0.000100","support","0","no","WebGPU"
"WebGPU: WebGPU","RMS_NORM","type=f32,ne=[1025,5,4,3],v=0,eps=0.000100,inplace=0","support","1","yes","WebGPU"
"WebGPU: WebGPU","NORM","type=f32,ne=[1025,5,4,3],v=1,eps=0.000100","support","0","no","WebGPU"
"WebGPU: WebGPU","RMS_NORM","type=f32,ne=[1025,5,4,3],v=1,eps=0.000100,inplace=0","support","1","yes","WebGPU"
"WebGPU: WebGPU","RMS_NORM_BACK","type=f32,ne=[1025,5,4,3],eps=0.000100","support","0","no","WebGPU"
"WebGPU: WebGPU","L2_NORM","type=f32,ne=[1025,5,4,3]","support","0","no","WebGPU"
"WebGPU: WebGPU","L2_NORM","type=f32,ne=[1025,5,4,3],eps=0.000100,v=0","support","1","yes","WebGPU"
"WebGPU: WebGPU","L2_NORM","type=f32,ne=[1025,5,4,3],eps=0.000100,v=1","support","1","yes","WebGPU"
"WebGPU: WebGPU","NORM","type=f32,ne=[64,5,4,3],v=0,eps=0.100000","support","0","no","WebGPU"
"WebGPU: WebGPU","RMS_NORM","type=f32,ne=[64,5,4,3],v=0,eps=0.100000,inplace=0","support","1","yes","WebGPU"
"WebGPU: WebGPU","NORM","type=f32,ne=[64,5,4,3],v=1,eps=0.100000","support","0","no","WebGPU"
"WebGPU: WebGPU","RMS_NORM","type=f32,ne=[64,5,4,3],v=1,eps=0.100000,inplace=0","support","1","yes","WebGPU"
"WebGPU: WebGPU","RMS_NORM_BACK","type=f32,ne=[64,5,4,3],eps=0.100000","support","0","no","WebGPU"
"WebGPU: WebGPU","L2_NORM","type=f32,ne=[64,5,4,3]","support","0","no","WebGPU"
"WebGPU: WebGPU","L2_NORM","type=f32,ne=[64,5,4,3],eps=0.100000,v=0","support","1","yes","WebGPU"
"WebGPU: WebGPU","L2_NORM","type=f32,ne=[64,5,4,3],eps=0.100000,v=1","support","1","yes","WebGPU"
"WebGPU: WebGPU","NORM","type=f32,ne=[1025,5,4,3],v=0,eps=0.100000","support","0","no","WebGPU"
"WebGPU: WebGPU","RMS_NORM","type=f32,ne=[1025,5,4,3],v=0,eps=0.100000,inplace=0","support","1","yes","WebGPU"
"WebGPU: WebGPU","NORM","type=f32,ne=[1025,5,4,3],v=1,eps=0.100000","support","0","no","WebGPU"
"WebGPU: WebGPU","RMS_NORM","type=f32,ne=[1025,5,4,3],v=1,eps=0.100000,inplace=0","support","1","yes","WebGPU"
"WebGPU: WebGPU","RMS_NORM_BACK","type=f32,ne=[1025,5,4,3],eps=0.100000","support","0","no","WebGPU"
"WebGPU: WebGPU","L2_NORM","type=f32,ne=[1025,5,4,3]","support","0","no","WebGPU"
"WebGPU: WebGPU","L2_NORM","type=f32,ne=[1025,5,4,3],eps=0.100000,v=0","support","1","yes","WebGPU"
"WebGPU: WebGPU","L2_NORM","type=f32,ne=[1025,5,4,3],eps=0.100000,v=1","support","1","yes","WebGPU"
"WebGPU: WebGPU","L2_NORM","type=f32,ne=[64,5,4,3],eps=10.000000,v=0","support","1","yes","WebGPU"
"WebGPU: WebGPU","L2_NORM","type=f32,ne=[64,5,4,3],eps=10.000000,v=1","support","1","yes","WebGPU"
"WebGPU: WebGPU","L2_NORM","type=f32,ne=[1025,5,4,3],eps=10.000000,v=0","support","1","yes","WebGPU"
"WebGPU: WebGPU","L2_NORM","type=f32,ne=[1025,5,4,3],eps=10.000000,v=1","support","1","yes","WebGPU"
"WebGPU: WebGPU","RMS_NORM","type=f32,ne=[64,5,4,3],v=0,eps=0.000001,inplace=1","support","1","yes","WebGPU"
"WebGPU: WebGPU","SSM_CONV","type=f32,ne_a=[3,1024,1,1],ne_b=[3,1024,1,1]","support","0","no","WebGPU"
"WebGPU: WebGPU","SSM_CONV","type=f32,ne_a=[6,1024,1,1],ne_b=[3,1024,1,1]","support","0","no","WebGPU"

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