cleanup

Author: gshtras

benchmarks/P3L.py

@@ -1,5 +1,6 @@
 #!/usr/bin/env python3
 # SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
 """
 Patch-Perplexity (P3L)
 

benchmarks/P3L_mling.py

@@ -1,5 +1,6 @@
 #!/usr/bin/env python3
 # SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
 """
 *MULTILINGUAL*  Patch-Perplexity (P3L)
 

benchmarks/profiling/benchmark_latency.py

@@ -1,4 +1,5 @@
 # SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
 """Benchmark the latency of processing a single batch of requests."""
 
 import argparse

benchmarks/profiling/benchmark_throughput.py

@@ -1,4 +1,5 @@
 # SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
 """Benchmark offline inference throughput."""
 
 import argparse

csrc/layernorm_kernels.cu

@@ -197,7 +197,7 @@ fused_add_rms_norm_kernel(
 #define LAUNCH_RMS_NORM(width)                                               \
   VLLM_DISPATCH_FLOATING_TYPES(input.scalar_type(), "rms_norm_kernel", [&] { \
     vllm::rms_norm_kernel<scalar_t, width><<<grid, block, 0, stream>>>(      \
-        out.data_ptr<scalar_t>(), input.data_ptr<scalar_t>(), input_strtide, \
+        out.data_ptr<scalar_t>(), input.data_ptr<scalar_t>(), input_stride,  \
         weight.data_ptr<scalar_t>(), epsilon, num_tokens, hidden_size,       \
         vec_hidden_size);                                                    \
   });