add tensorrt_llm common and cutlass_extensions as 3rdparty (#3216)

Co-authored-by: BBuf <35585791+BBuf@users.noreply.github.com>

add tensorrt_llm common and cutlass_extensions as 3rdparty (#3216)
Co-authored-by: BBuf <35585791+BBuf@users.noreply.github.com>
222ce6f1 · Yineng Zhang · GitHub · 468d23cf · 222ce6f1 · 222ce6f1
Unverified Commit 222ce6f1 authored Jan 30, 2025 by Yineng Zhang Committed by GitHub Jan 30, 2025
6 changed files
--- a/sgl-kernel/3rdparty/tensorrt_llm/cutlass_extensions/include/cutlass_extensions/tile_interleaved_layout.h
+++ b/sgl-kernel/3rdparty/tensorrt_llm/cutlass_extensions/include/cutlass_extensions/tile_interleaved_layout.h
--- a/sgl-kernel/3rdparty/tensorrt_llm/cutlass_extensions/include/cutlass_extensions/transform/threadblock/fine_grained_scale_zero_iterator.h
+++ b/sgl-kernel/3rdparty/tensorrt_llm/cutlass_extensions/include/cutlass_extensions/transform/threadblock/fine_grained_scale_zero_iterator.h
--- a/sgl-kernel/3rdparty/tensorrt_llm/cutlass_extensions/include/cutlass_extensions/util/gather_tensor.hpp
+++ b/sgl-kernel/3rdparty/tensorrt_llm/cutlass_extensions/include/cutlass_extensions/util/gather_tensor.hpp
--- a/sgl-kernel/3rdparty/tensorrt_llm/cutlass_extensions/include/cutlass_extensions/weight_only_quant_op.h
+++ b/sgl-kernel/3rdparty/tensorrt_llm/cutlass_extensions/include/cutlass_extensions/weight_only_quant_op.h
--- a/sgl-kernel/THIRDPARTYNOTICES.txt
+++ b/sgl-kernel/THIRDPARTYNOTICES.txt
--- a/sgl-kernel/setup.py
+++ b/sgl-kernel/setup.py