mirror of
https://github.com/ggml-org/llama.cpp.git
synced 2025-11-18 11:46:58 +00:00
opencl: add initial mxfp4 support via mv (#15270)
* opencl: add reference `mul_mv_mxfp4_f32` * opencl: add reference `mul_mv_id` for mxfp4 * Q4_0 tranpose fix for Adreno --------- Co-authored-by: shawngu-quic <shawngu@qti.qualcomm.com>
This commit is contained in:
@@ -82,7 +82,9 @@ set(GGML_OPENCL_KERNELS
|
||||
mul_mv_q4_0_f32_1d_8x_flat
|
||||
mul_mv_q4_0_f32_1d_16x_flat
|
||||
mul_mv_q6_k
|
||||
mul_mv_mxfp4_f32
|
||||
mul_mv_id_q4_0_f32_8x_flat
|
||||
mul_mv_id_mxfp4_f32
|
||||
mul_mm_f32_f32_l4_lm
|
||||
mul_mm_f16_f32_l4_lm
|
||||
mul
|
||||
|
||||
Reference in New Issue
Block a user