L-electron-Rare/mlx
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

[CUDA] 3/5/6-bit quants for qmm_naive (#3352)

Browse Source
This commit is contained in:
Cheng
2026-04-01 20:13:01 +09:00
committed by GitHub
parent 5e2c44259f
commit 2ffafe07f4
8 changed files with 142 additions and 112 deletions
Download Patch File Download Diff File Expand all files Collapse all files
python/tests/cuda_skip.py
-1
View File
@@ -27,7 +27,6 @@ cuda_skip = {
"TestQuantized.test_qmm_shapes",
"TestQuantized.test_fp_qvm",
"TestQuantized.test_qvm",
"TestQuantized.test_qvm_splitk",
"TestQuantized.test_qmv_small_non_multiples",
"TestQuantized.test_small_matrix",
"TestExportImport.test_export_quantized_model",