Skip to content

BF16 Trellis implementation #484

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
ikawrakow wants to merge 4 commits into from
Closed

BF16 Trellis implementation #484

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
62d8dd9
If available, use bf16 for iq2_kt gemm/gemv
Jun 1, 2025
9890618
If available, use bf16 for iq3_kt gemm/gemv
Jun 2, 2025
0715919
BF16 for iq4_kt
Jun 2, 2025
061d064
If available, use bf16 for iq4_kt gemm/gemv
Jun 2, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
6 changes: 6 additions & 0 deletions ggml/src/ggml.c
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1585,6 +1585,8 @@ static const ggml_type_traits_t type_traits[GGML_TYPE_COUNT] = {
.vec_dot = vec_dot_iq2_kt_q8_k,
#ifdef __ARM_NEON
.vec_dot_type = GGML_TYPE_F16,
#elif defined __AVX512BF16__
.vec_dot_type = GGML_TYPE_BF16,
#else
.vec_dot_type = GGML_TYPE_F32,
#endif
Expand All @@ -1602,6 +1604,8 @@ static const ggml_type_traits_t type_traits[GGML_TYPE_COUNT] = {
.vec_dot = vec_dot_iq3_kt_q8_k,
#ifdef __ARM_NEON
.vec_dot_type = GGML_TYPE_F16,
#elif defined __AVX512BF16__
.vec_dot_type = GGML_TYPE_BF16,
#else
.vec_dot_type = GGML_TYPE_F32,
#endif
Expand All @@ -1619,6 +1623,8 @@ static const ggml_type_traits_t type_traits[GGML_TYPE_COUNT] = {
.vec_dot = vec_dot_iq4_kt_q8_k,
#ifdef __ARM_NEON
.vec_dot_type = GGML_TYPE_F16,
#elif defined __AVX512BF16__
.vec_dot_type = GGML_TYPE_BF16,
#else
.vec_dot_type = GGML_TYPE_F32,
#endif
Expand Down
Loading