[ROCm][Quant] Minimax-M3: Enable fp8_per_channel for bf16 weights on mi300x (#45854)
Signed-off-by: Hongxia Yang <hongxia.yang@amd.com> Signed-off-by: tjtanaa <tunjian.tan@embeddedllm.com> Co-authored-by: tjtanaa <tunjian.tan@embeddedllm.com>
This commit is contained in:
@@ -459,6 +459,7 @@ class RocmPlatform(Platform):
|
||||
"modelopt_mixed",
|
||||
"fp8_per_tensor",
|
||||
"fp8_per_block",
|
||||
"fp8_per_channel",
|
||||
"online",
|
||||
"gpt_oss_mxfp4",
|
||||
]
|
||||
|
||||
Reference in New Issue
Block a user