diff --git a/docker/rocm.Dockerfile b/docker/rocm.Dockerfile index 712646a1f24b..21b9484c1846 100644 --- a/docker/rocm.Dockerfile +++ b/docker/rocm.Dockerfile @@ -390,10 +390,7 @@ ENV SGLANG_USE_AITER=1 ENV SGLANG_USE_ROCM700A=1 ENV NCCL_MIN_NCHANNELS=112 -ENV VLLM_FP8_PADDING=1 -ENV VLLM_FP8_ACT_PADDING=1 -ENV VLLM_FP8_WEIGHT_PADDING=1 -ENV VLLM_FP8_REDUCE_CONV=1 +ENV ROCM_QUICK_REDUCE_QUANTIZATION=INT8 ENV TORCHINDUCTOR_MAX_AUTOTUNE=1 ENV TORCHINDUCTOR_MAX_AUTOTUNE_POINTWISE=1 diff --git a/docker/rocm720.Dockerfile b/docker/rocm720.Dockerfile index 9c75aed9ee0b..2626f19f4943 100644 --- a/docker/rocm720.Dockerfile +++ b/docker/rocm720.Dockerfile @@ -496,10 +496,7 @@ ENV SGLANG_USE_AITER=1 ENV SGLANG_USE_ROCM700A=1 ENV NCCL_MIN_NCHANNELS=112 -ENV VLLM_FP8_PADDING=1 -ENV VLLM_FP8_ACT_PADDING=1 -ENV VLLM_FP8_WEIGHT_PADDING=1 -ENV VLLM_FP8_REDUCE_CONV=1 +ENV ROCM_QUICK_REDUCE_QUANTIZATION=INT8 ENV TORCHINDUCTOR_MAX_AUTOTUNE=1 ENV TORCHINDUCTOR_MAX_AUTOTUNE_POINTWISE=1