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

CUDA: fix external compilation of q1_0 MMQ (#25778)

Browse Source
This commit is contained in:
Johannes Gäßler
2026-07-23 14:45:51 +02:00
committed by GitHub
parent e6dd0e29a6
commit 1425386fd9
2 changed files with 25 additions and 15 deletions
Download Patch File Download Diff File Expand all files Collapse all files
ggml/src/ggml-cuda/mmq.cu
+18 -12
View File
@@ -25,12 +25,7 @@ static void ggml_cuda_mul_mat_q_switch_type(ggml_backend_cuda_context & ctx, con
case GGML_TYPE_Q8_0:
mul_mat_q_case<GGML_TYPE_Q8_0>(ctx, args, stream);
break;
case GGML_TYPE_MXFP4:
mul_mat_q_case<GGML_TYPE_MXFP4>(ctx, args, stream);
break;
case GGML_TYPE_NVFP4:
mul_mat_q_case<GGML_TYPE_NVFP4>(ctx, args, stream);
break;
// -----------------------------------------------------------------------
case GGML_TYPE_Q2_K:
mul_mat_q_case<GGML_TYPE_Q2_K>(ctx, args, stream);
break;
@@ -46,6 +41,10 @@ static void ggml_cuda_mul_mat_q_switch_type(ggml_backend_cuda_context & ctx, con
case GGML_TYPE_Q6_K:
mul_mat_q_case<GGML_TYPE_Q6_K>(ctx, args, stream);
break;
// -----------------------------------------------------------------------
case GGML_TYPE_IQ1_S:
mul_mat_q_case<GGML_TYPE_IQ1_S>(ctx, args, stream);
break;
case GGML_TYPE_IQ2_XXS:
mul_mat_q_case<GGML_TYPE_IQ2_XXS>(ctx, args, stream);
break;
@@ -61,15 +60,19 @@ static void ggml_cuda_mul_mat_q_switch_type(ggml_backend_cuda_context & ctx, con
case GGML_TYPE_IQ3_S:
mul_mat_q_case<GGML_TYPE_IQ3_S>(ctx, args, stream);
break;
case GGML_TYPE_IQ1_S:
mul_mat_q_case<GGML_TYPE_IQ1_S>(ctx, args, stream);
break;
case GGML_TYPE_IQ4_XS:
mul_mat_q_case<GGML_TYPE_IQ4_XS>(ctx, args, stream);
break;
case GGML_TYPE_IQ4_NL:
mul_mat_q_case<GGML_TYPE_IQ4_NL>(ctx, args, stream);
break;
// -----------------------------------------------------------------------
case GGML_TYPE_MXFP4:
mul_mat_q_case<GGML_TYPE_MXFP4>(ctx, args, stream);
break;
case GGML_TYPE_NVFP4:
mul_mat_q_case<GGML_TYPE_NVFP4>(ctx, args, stream);
break;
default:
GGML_ABORT("fatal error");
break;
@@ -264,21 +267,24 @@ bool ggml_cuda_should_use_mmq(enum ggml_type type, int cc, int64_t ne11, int64_t
case GGML_TYPE_Q5_0:
case GGML_TYPE_Q5_1:
case GGML_TYPE_Q8_0:
case GGML_TYPE_MXFP4:
case GGML_TYPE_NVFP4:
// -------------------------------------------------
case GGML_TYPE_Q2_K:
case GGML_TYPE_Q3_K:
case GGML_TYPE_Q4_K:
case GGML_TYPE_Q5_K:
case GGML_TYPE_Q6_K:
// -------------------------------------------------
case GGML_TYPE_IQ1_S:
case GGML_TYPE_IQ2_XXS:
case GGML_TYPE_IQ2_XS:
case GGML_TYPE_IQ2_S:
case GGML_TYPE_IQ3_XXS:
case GGML_TYPE_IQ3_S:
case GGML_TYPE_IQ1_S:
case GGML_TYPE_IQ4_XS:
case GGML_TYPE_IQ4_NL:
// -------------------------------------------------
case GGML_TYPE_MXFP4:
case GGML_TYPE_NVFP4:
mmq_supported = true;
break;
default: