Skip to content
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

Jump to bottom

Fix fusion bug #889

Merged
merged 2 commits into from
Jul 27, 2023
Merged

Fix fusion bug #889

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
12b0b70
fix
goliaro Jul 27, 2023
9b6d567
fix fusion bug for forward case too, add tests
goliaro Jul 27, 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
12 changes: 8 additions & 4 deletions src/ops/fused.cu
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -235,13 +235,15 @@ __host__ void FusedOp::forward_task(Task const *task,
out_dim * batch_size);
assert(my_input_accessor[0].domain.get_volume() == in_dim * batch_size);
float const *bias_ptr = nullptr;
LinearMeta *m = (LinearMeta *)metas->meta[op];
if (fused->op_num_weights[op] == 2) {
assert(my_weight_accessor[1].domain.get_volume() == out_dim);
bias_ptr = my_weight_accessor[1].get_float_ptr();
if (!m->add_bias_only_once || task->index_point.point_data[0] == 0) {
bias_ptr = my_weight_accessor[1].get_float_ptr();
}
} else {
assert(fused->op_num_weights[op] == 1);
}
LinearMeta *m = (LinearMeta *)metas->meta[op];
Kernels::Linear::forward_kernel_wrapper(
m,
my_input_accessor[0].get_float_ptr(),
Expand Down Expand Up @@ -604,13 +606,15 @@ __host__ void
out_dim * batch_size);
assert(my_input_accessor[0].domain.get_volume() == in_dim * batch_size);
void const *bias_ptr = nullptr;
LinearMeta *m = (LinearMeta *)metas->meta[op];
if (fused->op_num_weights[op] == 2) {
assert(my_weight_accessor[1].domain.get_volume() == out_dim);
bias_ptr = my_weight_accessor[1].ptr;
if (!m->add_bias_only_once || task->index_point.point_data[0] == 0) {
bias_ptr = my_weight_accessor[1].ptr;
}
} else {
assert(fused->op_num_weights[op] == 1);
}
LinearMeta *m = (LinearMeta *)metas->meta[op];
assert(m->input_type[0] == my_input_accessor[0].data_type);
assert(m->input_type[0] == my_output_accessor[0].data_type);
batch_size = bc->num_active_tokens();
Expand Down
4 changes: 4 additions & 0 deletions tests/inference_tests.sh
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -87,8 +87,10 @@ fi
if [ "$TENSOR_PARALLELISM_TESTS" = "ON" ]; then
# LLAMA (small model)
../build/inference/incr_decoding/incr_decoding -ll:gpu 4 -ll:fsize 14000 -ll:zsize 30000 --use-full-precision -llm-model llama -llm-weight ../inference/weights/llama_160M_weights/ -llm-config ../inference/models/configs/llama_160M.json -tokenizer ../inference/tokenizer/tokenizer.model -prompt ../inference/prompt/test.json -output-file ../inference/output/incr_decoding_llama_160M_tp.txt -pipeline-parallelism-degree 2 -tensor-parallelism-degree 2
../build/inference/incr_decoding/incr_decoding -ll:gpu 4 -ll:fsize 14000 -ll:zsize 30000 --use-full-precision -llm-model llama -llm-weight ../inference/weights/llama_160M_weights/ -llm-config ../inference/models/configs/llama_160M.json -tokenizer ../inference/tokenizer/tokenizer.model -prompt ../inference/prompt/test.json -output-file ../inference/output/incr_decoding_llama_160M_tp4.txt -pipeline-parallelism-degree 1 -tensor-parallelism-degree 4
# LLAMA (small model, half precision)
../build/inference/incr_decoding/incr_decoding -ll:gpu 4 -ll:fsize 14000 -ll:zsize 30000 -llm-model llama -llm-weight ../inference/weights/llama_160M_weights_half/ -llm-config ../inference/models/configs/llama_160M.json -tokenizer ../inference/tokenizer/tokenizer.model -prompt ../inference/prompt/test.json -output-file ../inference/output/incr_decoding_llama_160M_half_tp.txt -pipeline-parallelism-degree 2 -tensor-parallelism-degree 2
../build/inference/incr_decoding/incr_decoding -ll:gpu 4 -ll:fsize 14000 -ll:zsize 30000 -llm-model llama -llm-weight ../inference/weights/llama_160M_weights_half/ -llm-config ../inference/models/configs/llama_160M.json -tokenizer ../inference/tokenizer/tokenizer.model -prompt ../inference/prompt/test.json -output-file ../inference/output/incr_decoding_llama_160M_half_tp4.txt -pipeline-parallelism-degree 1 -tensor-parallelism-degree 4

# LLAMA (big model)
../build/inference/incr_decoding/incr_decoding -ll:gpu 4 -ll:fsize 14000 -ll:zsize 30000 --use-full-precision -llm-model llama -llm-weight ../inference/weights/llama_7B_weights/ -llm-config ../inference/models/configs/llama_7B.json -tokenizer ../inference/tokenizer/tokenizer.model -prompt ../inference/prompt/test.json -output-file ../inference/output/incr_decoding_llama_7B_tp.txt -pipeline-parallelism-degree 2 -tensor-parallelism-degree 2
Expand All @@ -97,8 +99,10 @@ if [ "$TENSOR_PARALLELISM_TESTS" = "ON" ]; then

# OPT (small model)
../build/inference/incr_decoding/incr_decoding -ll:gpu 4 -ll:fsize 14000 -ll:zsize 30000 --use-full-precision -llm-model opt -llm-weight ../inference/weights/opt_125M_weights/ -llm-config ../inference/models/configs/opt_125M.json -tokenizer ../inference/tokenizer/ -prompt ../inference/prompt/test.json -output-file ../inference/output/incr_decoding_opt_125M_tp.txt -pipeline-parallelism-degree 2 -tensor-parallelism-degree 2
../build/inference/incr_decoding/incr_decoding -ll:gpu 4 -ll:fsize 14000 -ll:zsize 30000 --use-full-precision -llm-model opt -llm-weight ../inference/weights/opt_125M_weights/ -llm-config ../inference/models/configs/opt_125M.json -tokenizer ../inference/tokenizer/ -prompt ../inference/prompt/test.json -output-file ../inference/output/incr_decoding_opt_125M_tp4.txt -pipeline-parallelism-degree 1 -tensor-parallelism-degree 4
# OPT (small model, half precision)
../build/inference/incr_decoding/incr_decoding -ll:gpu 4 -ll:fsize 14000 -ll:zsize 30000 -llm-model opt -llm-weight ../inference/weights/opt_125M_weights_half/ -llm-config ../inference/models/configs/opt_125M.json -tokenizer ../inference/tokenizer/ -prompt ../inference/prompt/test.json -output-file ../inference/output/incr_decoding_opt_125M_half_tp.txt -pipeline-parallelism-degree 2 -tensor-parallelism-degree 2
../build/inference/incr_decoding/incr_decoding -ll:gpu 4 -ll:fsize 14000 -ll:zsize 30000 -llm-model opt -llm-weight ../inference/weights/opt_125M_weights_half/ -llm-config ../inference/models/configs/opt_125M.json -tokenizer ../inference/tokenizer/ -prompt ../inference/prompt/test.json -output-file ../inference/output/incr_decoding_opt_125M_half_tp.txt -pipeline-parallelism-degree 1 -tensor-parallelism-degree 4

# OPT (big model)
../build/inference/incr_decoding/incr_decoding -ll:gpu 4 -ll:fsize 14000 -ll:zsize 30000 --use-full-precision -llm-model opt -llm-weight ../inference/weights/opt_6B_weights/ -llm-config ../inference/models/configs/opt_6B.json -tokenizer ../inference/tokenizer/ -prompt ../inference/prompt/test.json -output-file ../inference/output/incr_decoding_opt_6B_tp.txt -pipeline-parallelism-degree 2 -tensor-parallelism-degree 2
Expand Down
Loading