diff --git a/docker/Dockerfile.rocm b/docker/Dockerfile.rocm index 001c2ccd3..45c0fef54 100644 --- a/docker/Dockerfile.rocm +++ b/docker/Dockerfile.rocm @@ -42,7 +42,7 @@ ENV BUILD_TRITON="0" ENV BUILD_LLVM="0" ENV BUILD_AITER_ALL="1" ENV BUILD_MOONCAKE="1" -ENV AITER_COMMIT="v0.1.5.post3" +ENV AITER_COMMIT="v0.1.5.post4" ENV NO_DEPS_FLAG="--no-deps" # =============================== diff --git a/python/sglang/srt/model_executor/model_runner.py b/python/sglang/srt/model_executor/model_runner.py index 3c5946578..42dfaecf7 100644 --- a/python/sglang/srt/model_executor/model_runner.py +++ b/python/sglang/srt/model_executor/model_runner.py @@ -536,9 +536,7 @@ class ModelRunner: elif _is_hip: head_num = self.model_config.get_num_kv_heads(self.tp_size) # TODO current aiter only support head number 16 or 128 head number - if ( - head_num == 128 or head_num == 16 - ) and self.spec_algorithm.is_none(): + if head_num == 128 or head_num == 16: server_args.attention_backend = "aiter" else: server_args.attention_backend = "triton"