metal: Q1_0 backend (#21528)
* initial Q1_0 Metal backend * tuning q1_0 metal kernels * add Q1_0 to test-backend-ops * add Q1_0<->F32 copy test * Apply suggestions from code review Co-authored-by: Georgi Gerganov <ggerganov@gmail.com> --------- Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
This commit is contained in:
@@ -7251,6 +7251,7 @@ static const ggml_type all_types[] = {
|
||||
GGML_TYPE_Q4_0, GGML_TYPE_Q4_1,
|
||||
GGML_TYPE_Q5_0, GGML_TYPE_Q5_1,
|
||||
GGML_TYPE_Q8_0,
|
||||
GGML_TYPE_Q1_0,
|
||||
GGML_TYPE_MXFP4, GGML_TYPE_NVFP4,
|
||||
GGML_TYPE_Q2_K, GGML_TYPE_Q3_K,
|
||||
GGML_TYPE_Q4_K, GGML_TYPE_Q5_K,
|
||||
@@ -7275,6 +7276,7 @@ static const ggml_type other_types[] = {
|
||||
GGML_TYPE_Q4_1,
|
||||
GGML_TYPE_Q5_0, GGML_TYPE_Q5_1,
|
||||
GGML_TYPE_Q8_0,
|
||||
GGML_TYPE_Q1_0,
|
||||
GGML_TYPE_Q2_K, GGML_TYPE_Q3_K,
|
||||
GGML_TYPE_Q5_K,
|
||||
GGML_TYPE_Q6_K,
|
||||
|
||||
Reference in New Issue
Block a user