ggml-cpu: add RVV vec dot kernels for quantization types (#18859)
* ggml-cpu: add rvv quantize_row_q8_K kernel Co-authored-by: Rehan Qasim <rehan.qasim@10xengineers.ai> * ggml-cpu: add rvv vec_dot for iq4_nl, mxfp4, iq2_xxs Co-authored-by: Rehan Qasim <rehan.qasim@10xengineers.ai> * ggml-cpu: add rvv vec_dot for iq4_xs, refactor * ggml-cpu: remove ifunc for rvv vec dot * ggml-cpu: add vec_dot for iq2_xs, iq3_xxs Co-authored-by: Rehan Qasim <rehan.qasim@10xengineers.ai> * ggml-cpu: refactor quants.c --------- Co-authored-by: taimur-10x <taimur.ahmad@10xengineers.ai> Co-authored-by: Rehan Qasim <rehan.qasim@10xengineers.ai> Co-authored-by: Rehan Qasim <rehanbhatti0317@gmail.com>
This commit is contained in:
parent
b5e1212063
commit
fbaa95bc29
|
|
@ -199,13 +199,6 @@
|
|||
#define ggml_gemm_q8_0_4x8_q8_0_generic ggml_gemm_q8_0_4x8_q8_0
|
||||
#elif defined(__riscv)
|
||||
// quants.c
|
||||
#define quantize_row_q8_K_generic quantize_row_q8_K
|
||||
#define ggml_vec_dot_iq2_xxs_q8_K_generic ggml_vec_dot_iq2_xxs_q8_K
|
||||
#define ggml_vec_dot_iq2_xs_q8_K_generic ggml_vec_dot_iq2_xs_q8_K
|
||||
#define ggml_vec_dot_iq3_xxs_q8_K_generic ggml_vec_dot_iq3_xxs_q8_K
|
||||
#define ggml_vec_dot_iq4_nl_q8_0_generic ggml_vec_dot_iq4_nl_q8_0
|
||||
#define ggml_vec_dot_iq4_xs_q8_K_generic ggml_vec_dot_iq4_xs_q8_K
|
||||
#define ggml_vec_dot_mxfp4_q8_0_generic ggml_vec_dot_mxfp4_q8_0
|
||||
#define ggml_vec_dot_nvfp4_q8_0_generic ggml_vec_dot_nvfp4_q8_0
|
||||
// repack.cpp
|
||||
#define ggml_quantize_mat_q8_0_4x1_generic ggml_quantize_mat_q8_0_4x1
|
||||
|
|
|
|||
File diff suppressed because it is too large
Load Diff
Loading…
Reference in New Issue