Commit Graph
6 Commits
Author SHA1 Message Date
Shawn GuandGitHub 0f3cb3fc8b opencl: generalize Adreno MoE kernels on M (#23449) 2026-05-22 17:08:41 -07:00
1ec7ba0c14 opencl: add q4_1 MoE for Adreno (#22856)
* Q4_1 MoE CLC pass sanity check

* remove unnecessary code

* opencl: remove unnecessary asserts and reformat

* opencl: fix supports_op for q4_1 moe

* q4_1 moe is supported by Adreno with certain shapes

---------

Co-authored-by: Li He <lih@qti.qualcomm.com>
2026-05-11 11:57:26 -07:00
f3e8d149ce opencl: add q4_0 MoE GEMM for Adreno (#22731)
* Q4_0 MoE CLC pass sanity check

* release program

* opencl: fix whitespace

* opencl: remove unused cl_program

* opencl: break #if block to make it more clear

* opencl: adjust format

---------

Co-authored-by: Li He <lih@qti.qualcomm.com>
2026-05-07 21:17:07 -07:00
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
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