Skip to content

GitLab

Unverified Commit 740a2bc6 authored by Charlie Lin's avatar Charlie Lin Committed by GitHub
Browse files

Merge branch 'develop' into dyn_gemm

parents 2af03c23 4420ccbd
Hide whitespace changes
Inline Side-by-side
Showing with 1 addition and 3 deletions
examples/nlp/python_bert_squad/requirements_bertsquad.txt
View file @ 740a2bc6
...@@ -21,6 +21,6 @@ ...@@ -21,6 +21,6 @@
# OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN # OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
# THE SOFTWARE. # THE SOFTWARE.
##################################################################################### #####################################################################################
tensorflow==2.7.2 tensorflow==2.9.3
onnxruntime onnxruntime
tokenizers tokenizers
\ No newline at end of file
src/targets/gpu/target.cpp
View file @ 740a2bc6
...@@ -146,8 +146,6 @@ std::vector<pass> target::get_passes(migraphx::context& gctx, const compile_opti ...@@ -146,8 +146,6 @@ std::vector<pass> target::get_passes(migraphx::context& gctx, const compile_opti
dead_code_elimination{}, dead_code_elimination{},
pack_int8_args{}, pack_int8_args{},
dead_code_elimination{}, dead_code_elimination{},
adjust_allocation{gpu_allocation_model{}},
dead_code_elimination{},
fuse_ops{&ctx, options.fast_math}, fuse_ops{&ctx, options.fast_math},
dead_code_elimination{}, dead_code_elimination{},
replace_allocate{gpu_allocation_model{}, options.offload_copy}, replace_allocate{gpu_allocation_model{}, options.offload_copy},
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment