Lumpiasty/llama.cpp
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

cuda: Q1_0 initial backend (#21629)

Browse Source 
* [cuda] initial Q1_0 backend

* remove unused code, fix AMD MMA guard

* attempt to support dp4a

* Apply suggestions from code review

Co-authored-by: Johannes Gäßler <johannesg@5d6.de>

---------

Co-authored-by: Johannes Gäßler <johannesg@5d6.de>
This commit is contained in:
Pasha Khosravi
2026-04-15 18:38:38 +02:00
committed by GitHub
co-authored by Johannes Gäßler
parent 20d3bc2cc8
commit 7e72b38bc1
11 changed files with 204 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
ggml/src/ggml-cuda/mmq.cu
+4
View File
@@ -5,6 +5,9 @@
static void ggml_cuda_mul_mat_q_switch_type(ggml_backend_cuda_context & ctx, const mmq_args & args, cudaStream_t stream) {
switch (args.type_x) {
case GGML_TYPE_Q1_0:
mul_mat_q_case<GGML_TYPE_Q1_0>(ctx, args, stream);
break;
case GGML_TYPE_Q4_0:
mul_mat_q_case<GGML_TYPE_Q4_0>(ctx, args, stream);
break;
@@ -270,6 +273,7 @@ bool ggml_cuda_should_use_mmq(enum ggml_type type, int cc, int64_t ne11, int64_t
bool mmq_supported;
switch (type) {
case GGML_TYPE_Q1_0:
case GGML_TYPE_Q4_0:
case GGML_TYPE_Q4_1:
case GGML_TYPE_Q5_0: