Merge branch 'feature/add-splitkv-instance' into...

Merge branch 'feature/add-splitkv-instance' into feature/support-vllm-kcache-layout-add-splitkv-instance

Merge branch 'feature/add-splitkv-instance' into...
Merge branch 'feature/add-splitkv-instance' into feature/support-vllm-kcache-layout-add-splitkv-instance
43596386 · Po Yen Chen · 250399cd · af07d650 · 43596386 · 43596386
Commit 43596386 authored Dec 19, 2024 by Po Yen Chen
20 changed files
--- a/include/ck_tile/ops/fmha/kernel/fmha_fwd_splitkv_kernel.hpp
+++ b/include/ck_tile/ops/fmha/kernel/fmha_fwd_splitkv_kernel.hpp
--- a/include/ck_tile/ops/fused_moe/pipeline/fused_moegemm_pipeline_flatmm_policy.hpp
+++ b/include/ck_tile/ops/fused_moe/pipeline/fused_moegemm_pipeline_flatmm_policy.hpp
--- a/include/ck_tile/ops/fused_moe/pipeline/fused_moegemm_traits.hpp
+++ b/include/ck_tile/ops/fused_moe/pipeline/fused_moegemm_traits.hpp
--- a/include/ck_tile/ops/gemm.hpp
+++ b/include/ck_tile/ops/gemm.hpp
--- a/include/ck_tile/ops/gemm/kernel/gemm_kernel.hpp
+++ b/include/ck_tile/ops/gemm/kernel/gemm_kernel.hpp
--- a/include/ck_tile/ops/gemm/kernel/gemm_tile_partitioner.hpp
+++ b/include/ck_tile/ops/gemm/kernel/gemm_tile_partitioner.hpp
--- a/include/ck_tile/ops/gemm/kernel/grouped_gemm_kernel.hpp
+++ b/include/ck_tile/ops/gemm/kernel/grouped_gemm_kernel.hpp
--- a/include/ck_tile/ops/smoothquant/kernel/smoothquant_kernel.hpp
+++ b/include/ck_tile/ops/smoothquant/kernel/smoothquant_kernel.hpp
--- a/include/ck_tile/ref/README.md
+++ b/include/ck_tile/ref/README.md
--- a/include/ck_tile/ref/naive_attention.hpp
+++ b/include/ck_tile/ref/naive_attention.hpp
--- a/include/ck_tile/remod.py
+++ b/include/ck_tile/remod.py
--- a/library/include/ck/library/reference_tensor_operation/cpu/reference_gemm.hpp
+++ b/library/include/ck/library/reference_tensor_operation/cpu/reference_gemm.hpp
--- a/library/src/tensor_operation_instance/gpu/CMakeLists.txt
+++ b/library/src/tensor_operation_instance/gpu/CMakeLists.txt
--- a/library/src/tensor_operation_instance/gpu/gemm_universal_batched/device_batched_gemm_xdl_universal_bf16_bf16_bf16/device_batched_gemm_xdl_universal_bf16_bf16_bf16_mk_nk_mn.hpp
+++ b/library/src/tensor_operation_instance/gpu/gemm_universal_batched/device_batched_gemm_xdl_universal_bf16_bf16_bf16/device_batched_gemm_xdl_universal_bf16_bf16_bf16_mk_nk_mn.hpp
--- a/library/src/tensor_operation_instance/gpu/gemm_universal_batched/device_batched_gemm_xdl_universal_f8_f8_bf16/device_batched_gemm_xdl_universal_f8_f8_bf16_mk_nk_mn.hpp
+++ b/library/src/tensor_operation_instance/gpu/gemm_universal_batched/device_batched_gemm_xdl_universal_f8_f8_bf16/device_batched_gemm_xdl_universal_f8_f8_bf16_mk_nk_mn.hpp
--- a/library/src/tensor_operation_instance/gpu/mha/CMakeLists.txt
+++ b/library/src/tensor_operation_instance/gpu/mha/CMakeLists.txt
--- a/library/src/tensor_operation_instance/gpu/pool3d_fwd/device_max_pool3d_fwd_ndhwc_f8_instance.cpp
+++ b/library/src/tensor_operation_instance/gpu/pool3d_fwd/device_max_pool3d_fwd_ndhwc_f8_instance.cpp
--- a/modified_files.txt
+++ b/modified_files.txt
--- a/profiler/README.md
+++ b/profiler/README.md
--- a/profiler/include/profiler/profile_batched_gemm_bias_softmax_gemm_permute_impl.hpp
+++ b/profiler/include/profiler/profile_batched_gemm_bias_softmax_gemm_permute_impl.hpp