Skip to content

[SYCL] Update unsupported quantization types #5750

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.

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
Closed
Changes from all commits
Commits
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
14 changes: 13 additions & 1 deletion ggml-sycl.cpp
Original file line number Diff line number Diff line change
Expand Up @@ -12010,7 +12010,10 @@ inline void ggml_sycl_op_mul_mat_vec_q(
GGML_ASSERT(!(src0->type == GGML_TYPE_IQ2_XXS ||
src0->type == GGML_TYPE_IQ2_XS ||
src0->type == GGML_TYPE_IQ3_XXS ||
src0->type == GGML_TYPE_IQ1_S));
src0->type == GGML_TYPE_IQ1_S ||
src0->type == GGML_TYPE_IQ2_S ||
src0->type == GGML_TYPE_IQ3_S ||
src0->type == GGML_TYPE_IQ4_NL));

switch (src0->type) {
case GGML_TYPE_Q4_0:
Expand Down Expand Up @@ -15051,6 +15054,15 @@ static bool ggml_backend_sycl_supports_op(ggml_backend_t backend, const ggml_ten
if (a->type == GGML_TYPE_IQ1_S) {
return false;
}
if (a->type == GGML_TYPE_IQ2_S) {
return false;
}
if (a->type == GGML_TYPE_IQ3_S) {
return false;
}
if (a->type == GGML_TYPE_IQ4_NL) {
return false;
}
if (a->type == GGML_TYPE_IQ3_XXS) {
return false;
}
Expand Down