nikola/llama_cpp
1
0
Fork 0
Code Issues Pull Requests Actions 23 Packages Projects Releases Wiki Activity
9,039 Commits 1 Branch 0 Tags
74d6248f71718ebd73599b8b859ed2f1847d60b1
Commit Graph
3 Commits
This Branch
This Branch
All Branches
Author SHA1 Message Date
Shawn GuGitHubLi He
 		c5a3bc39b1 opencl: Adreno optimization for MoE - MxFP4 (#22301) 
* MoE Mxfp4 CLC kernel added, router reorder on GPU

* Pass test-backend-ops for MoE mxfp4 Adreno CLC

* remove putenv in llama-model.cpp

* fix indent style and whitespace

* opencl: remove unnecessary headers

* opencl: do not save cl_program objects

* opencl: remove unnecessary assert

* fix precision issue

---------

Co-authored-by: Li He <lih@qti.qualcomm.com>
 2026-05-01 23:02:24 -07:00
Shawn GuandGitHub 81387858f1 opencl: transposed gemm/gemv moe kernel with mxfp4,f32 (#16602) 
* opencl: transposed gemm/gemv moe kernel with mxfp4,f32

* add restore kernel for moe transpose

* fix trailing whitespaces

* resolve compilation warnings
 2025-10-17 17:55:32 -07:00
Shawn GuGitHubLi He
 		3edd87cd05 opencl: optimize mxfp4 kernels (#16037) 
- flatten mxfp4 and packed fp4->fp16 bit-wise convert function (replace lut)
- MoE kernel optimizations

---------

Co-authored-by: Li He <lih@qti.qualcomm.com>
 2025-09-18 12:03:34 -07:00