Commit 73fecd7
committed
WeightOnlyLooper supports multi-GPU and multi-threading acceleration for quantization
Signed-off-by: ZX-ModelCloud <zx@modelcloud.ai>1 parent 5b064ac commit 73fecd7
3 files changed
Lines changed: 594 additions & 24 deletions
File tree
- gptqmodel/looper
- tests
0 commit comments