[Quantization] Support native Quark W4A16 INT4/UINT4 exports in vLLM (#48606)
Signed-off-by: HongWei Meng <HongWei.Meng@amd.com>
This commit is contained in:
@@ -864,6 +864,7 @@ def choose_mp_linear_kernel(
|
||||
|
||||
can_implement, failure_reason = kernel.can_implement(config)
|
||||
if can_implement:
|
||||
logger.info_once("Using %s for mixed-precision linear", kernel.__name__)
|
||||
return kernel
|
||||
else:
|
||||
failure_reasons.append(
|
||||
|
||||
Reference in New Issue
Block a user