Divakar Verma a66cf40b20

[Kernel][ROCm][AMD] enable fused topk_softmax kernel for moe layer (#4927) ...

This PR enables the fused topk_softmax kernel used in moe layer for HIP

2024-06-02 14:13:26 -07:00

..

attention

[Model] Support MAP-NEO model (#5081)

2024-05-30 19:24:41 -07:00

cpu

[Model] Support MAP-NEO model (#5081)

2024-05-30 19:24:41 -07:00

moe

[Kernel][ROCm][AMD] enable fused topk_softmax kernel for moe layer (#4927)

2024-06-02 14:13:26 -07:00

punica

[Model] LoRA gptbigcode implementation (#3949)

2024-05-22 13:58:59 -07:00

quantization

[Kernel] Update Cutlass fp8 configs (#5144)

2024-06-01 08:46:07 +00:00

activation_kernels.cu

[CI/Build] Enforce style for C++ and CUDA code with clang-format (#4722)

2024-05-22 07:18:41 +00:00

cache_kernels.cu

[CI/Build] Enforce style for C++ and CUDA code with clang-format (#4722)

2024-05-22 07:18:41 +00:00

cache.h

[CI/Build] Enforce style for C++ and CUDA code with clang-format (#4722)

2024-05-22 07:18:41 +00:00

cuda_compat.h

[Kernel][ROCm][AMD] enable fused topk_softmax kernel for moe layer (#4927)

2024-06-02 14:13:26 -07:00

cuda_utils_kernels.cu

[CI/Build] Enforce style for C++ and CUDA code with clang-format (#4722)

2024-05-22 07:18:41 +00:00

cuda_utils.h

[CI/Build] Enforce style for C++ and CUDA code with clang-format (#4722)

2024-05-22 07:18:41 +00:00

custom_all_reduce_test.cu

[CI/Build] Enforce style for C++ and CUDA code with clang-format (#4722)

2024-05-22 07:18:41 +00:00

custom_all_reduce.cu

[CI/Build] Enforce style for C++ and CUDA code with clang-format (#4722)

2024-05-22 07:18:41 +00:00

custom_all_reduce.cuh

[CI/Build] Enforce style for C++ and CUDA code with clang-format (#4722)

2024-05-22 07:18:41 +00:00

dispatch_utils.h

[CI/Build] Enforce style for C++ and CUDA code with clang-format (#4722)

2024-05-22 07:18:41 +00:00

layernorm_kernels.cu

[CI/Build] Enforce style for C++ and CUDA code with clang-format (#4722)

2024-05-22 07:18:41 +00:00

moe_align_block_size_kernels.cu

[CI/Build] Enforce style for C++ and CUDA code with clang-format (#4722)

2024-05-22 07:18:41 +00:00

ops.h

[Kernel][Backend][Model] Blocksparse flash attention kernel and Phi-3-Small model (#4799)

2024-05-24 22:00:52 -07:00

pos_encoding_kernels.cu

[CI/Build] Enforce style for C++ and CUDA code with clang-format (#4722)

2024-05-22 07:18:41 +00:00

pybind.cpp

[Kernel] Initial Activation Quantization Support (#4525)

2024-05-23 21:29:18 +00:00

reduction_utils.cuh

[CI/Build] Enforce style for C++ and CUDA code with clang-format (#4722)

2024-05-22 07:18:41 +00:00