LLM-Inference/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-08-12 22:31:11 +04:00
Code Issues Packages Projects Releases Wiki Activity

ggml-cpu : fix missing Q5_0 dispatch in SpaceMiT backend (#26792)

Browse Source
This commit is contained in:
Hao-Chen2337
2026-08-09 18:16:53 +08:00
committed by GitHub
parent 61141f1487
commit 08659901c4
1 changed files with 2 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
ggml/src/ggml-cpu/spacemit/ime.cpp
+2
View File
@@ -195,6 +195,7 @@ template <typename BLOC_TYPE, int64_t INTER_SIZE, int64_t NB_COLS> class tensor_
case GGML_TYPE_Q4_K:
case GGML_TYPE_Q6_K:
case GGML_TYPE_Q8_0:
case GGML_TYPE_Q5_0:
case GGML_TYPE_Q5_1:
case GGML_TYPE_Q5_K:
//case GGML_TYPE_MXFP4:
@@ -214,6 +215,7 @@ template <typename BLOC_TYPE, int64_t INTER_SIZE, int64_t NB_COLS> class tensor_
case GGML_TYPE_Q4_K:
case GGML_TYPE_Q6_K:
case GGML_TYPE_Q8_0:
case GGML_TYPE_Q5_0:
case GGML_TYPE_Q5_1:
case GGML_TYPE_Q5_K:
//case GGML_TYPE_MXFP4: