mirror of
https://github.com/ggml-org/llama.cpp.git
synced 2026-09-11 04:56:56 +02:00
fix q4_0_8_8 format for corrupted tokens issue (#10198)
Co-authored-by: EC2 Default User <[email protected]>
This commit is contained in:
co-authored by
EC2 Default User
parent
3bcd40b3c5
commit
2319126a70
@@ -409,6 +409,8 @@ static const struct ggml_type_traits_cpu type_traits_cpu[GGML_TYPE_COUNT] = {
|
||||
.gemm = ggml_gemm_q4_0_4x8_q8_0,
|
||||
},
|
||||
[GGML_TYPE_Q4_0_8_8] = {
|
||||
.vec_dot = NULL,
|
||||
.vec_dot_type = GGML_TYPE_Q8_0,
|
||||
.nrows = 1,
|
||||
.ncols = 8,
|
||||
.gemv = ggml_gemv_q4_0_8x8_q8_0,
|
||||
|
||||
Reference in New Issue
Block a user