Skip to content

Support llama in triton fastertransformer backend #6

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 16 commits into from
Aug 28, 2023
Merged

Support llama in triton fastertransformer backend #6

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
16 commits
Select commit Hold shift + click to select a range
968920a
commit
sfc-gh-zhwang Aug 19, 2023
1d8b7fd
commit
sfc-gh-zhwang Aug 19, 2023
123933b
commit
sfc-gh-zhwang Aug 20, 2023
ab152e2
commit
sfc-gh-zhwang Aug 21, 2023
5db164b
commit
sfc-gh-zhwang Aug 21, 2023
27b9a36
commit
sfc-gh-zhwang Aug 24, 2023
314cc9d
commit
sfc-gh-zhwang Aug 24, 2023
ec8ba94
commit
sfc-gh-zhwang Aug 24, 2023
63cb0b6
commit
sfc-gh-zhwang Aug 24, 2023
25fbeb9
commit
sfc-gh-zhwang Aug 24, 2023
35b9388
commit
sfc-gh-zhwang Aug 24, 2023
d259efc
commit
sfc-gh-zhwang Aug 24, 2023
e0562b1
commit
sfc-gh-zhwang Aug 25, 2023
2d60bbe
commit
sfc-gh-zhwang Aug 28, 2023
d9125f2
Merge branch 'corvo' into zhwang/llama2
sfc-gh-zhwang Aug 28, 2023
31babb0
commit
sfc-gh-zhwang Aug 28, 2023
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion CMakeLists.txt
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -111,7 +111,7 @@ else()
FetchContent_Declare(
repo-ft
GIT_REPOSITORY https://github.com/neevaco/FasterTransformer.git
GIT_TAG main
GIT_TAG affa1ef1c175d03db8ff5b14824cc58dd2c52c2b
GIT_SHALLOW ON
)
endif()
Expand Down
16 changes: 16 additions & 0 deletions src/libfastertransformer.cc
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -54,6 +54,7 @@
#include "src/fastertransformer/triton_backend/gptj/GptJTritonModelInstance.h"
#include "src/fastertransformer/triton_backend/gptneox/GptNeoXTritonModel.h"
#include "src/fastertransformer/triton_backend/gptneox/GptNeoXTritonModelInstance.h"
#include "src/fastertransformer/triton_backend/llama/LlamaTritonModel.h"
#include "src/fastertransformer/triton_backend/multi_gpu_gpt/ParallelGptTritonModel.h"
#include "src/fastertransformer/triton_backend/multi_gpu_gpt/ParallelGptTritonModelInstance.h"
#include "src/fastertransformer/triton_backend/t5/T5TritonModel.h"
Expand Down Expand Up @@ -328,6 +329,21 @@ std::shared_ptr<AbstractTransformerModel> ModelState::ModelFactory(
} else if (data_type == "bf16") {
ft_model = std::make_shared<BertTritonModel<__nv_bfloat16>>(
tp, pp, custom_ar, model_dir, int8_mode, is_sparse, remove_padding);
#endif
}
} else if (model_type == "llama") {
const int int8_mode = param_get_int(param, "int8_mode");

if (data_type == "fp16") {
ft_model = std::make_shared<LlamaTritonModel<half>>(
tp, pp, custom_ar, model_dir, int8_mode);
} else if (data_type == "fp32") {
ft_model = std::make_shared<LlamaTritonModel<float>>(
tp, pp, custom_ar, model_dir, int8_mode);
#ifdef ENABLE_BF16
} else if (data_type == "bf16") {
ft_model = std::make_shared<LlamaTritonModel<__nv_bfloat16>>(
tp, pp, custom_ar, model_dir, int8_mode);
#endif
}
} else if (model_type == "deberta") {
Expand Down