rename src/fastertransformer to src/turbomind (#33)

53d2e42c · lvhan028 · GitHub · fe46dac2 · 53d2e42c · 53d2e42c
Unverified Commit 53d2e42c authored Jul 01, 2023 by lvhan028 Committed by GitHub Jul 01, 2023
20 changed files
--- a/src/fastertransformer/models/llama/LlamaInstanceComm.h
+++ b/src/fastertransformer/models/llama/LlamaInstanceComm.h
--- a/src/fastertransformer/models/llama/LlamaLinear.h
+++ b/src/fastertransformer/models/llama/LlamaLinear.h
--- a/src/fastertransformer/models/llama/LlamaNcclGuard.h
+++ b/src/fastertransformer/models/llama/LlamaNcclGuard.h
--- a/src/fastertransformer/models/llama/LlamaV2.cc
+++ b/src/fastertransformer/models/llama/LlamaV2.cc
--- a/src/fastertransformer/models/llama/LlamaV2.h
+++ b/src/fastertransformer/models/llama/LlamaV2.h
--- a/src/fastertransformer/models/llama/LlamaWeight.cc
+++ b/src/fastertransformer/models/llama/LlamaWeight.cc
--- a/src/fastertransformer/models/llama/LlamaWeight.h
+++ b/src/fastertransformer/models/llama/LlamaWeight.h
--- a/src/fastertransformer/models/llama/Request.h
+++ b/src/fastertransformer/models/llama/Request.h
--- a/src/fastertransformer/models/llama/fused_multi_head_attention/CMakeLists.txt
+++ b/src/fastertransformer/models/llama/fused_multi_head_attention/CMakeLists.txt
--- a/src/fastertransformer/models/llama/fused_multi_head_attention/llama_flash_attention_kernel.cu
+++ b/src/fastertransformer/models/llama/fused_multi_head_attention/llama_flash_attention_kernel.cu
--- a/src/fastertransformer/models/llama/fused_multi_head_attention/mma_accum_lambda_iterator.h
+++ b/src/fastertransformer/models/llama/fused_multi_head_attention/mma_accum_lambda_iterator.h
--- a/src/fastertransformer/models/llama/fused_multi_head_attention/tile_smem_loader.h
+++ b/src/fastertransformer/models/llama/fused_multi_head_attention/tile_smem_loader.h
--- a/src/fastertransformer/models/llama/llama_decoder_kernels.cu
+++ b/src/fastertransformer/models/llama/llama_decoder_kernels.cu
--- a/src/fastertransformer/models/llama/llama_decoder_kernels.h
+++ b/src/fastertransformer/models/llama/llama_decoder_kernels.h
--- a/src/fastertransformer/models/llama/llama_gemm.cc
+++ b/src/fastertransformer/models/llama/llama_gemm.cc
--- a/src/fastertransformer/models/llama/llama_kernels.cu
+++ b/src/fastertransformer/models/llama/llama_kernels.cu
--- a/src/fastertransformer/models/llama/llama_kernels.h
+++ b/src/fastertransformer/models/llama/llama_kernels.h
--- a/src/fastertransformer/models/llama/llama_utils.cu
+++ b/src/fastertransformer/models/llama/llama_utils.cu
--- a/src/fastertransformer/models/llama/llama_utils.h
+++ b/src/fastertransformer/models/llama/llama_utils.h
--- a/src/fastertransformer/models/llama/prefix_cache.cu
+++ b/src/fastertransformer/models/llama/prefix_cache.cu