Go
Home
Pricing
FAQ
Install
Home
Pricing
FAQ
Install
Login
via GitHub
microsoft/onnxruntime
Pull Requests
Commits
gqa_attention
0
1.1.0-test
1.11.1-audio
AddLicenseHeader
AddThreadPoolAPIs
AddressScalarExpandTest
BlockSizeUpperBound
BoostExpand
BoostExpand2
BoostExpandCpu2
BoostExpandCpuTest
BoostMaxPool
BoostMaxPoolWithClassifier
BuildPython38
CachePingPong
Cjian/Conv_FP_16_Python_Converter
Cjian/Refactor_pipeline
Cjian/ad
Cjian/bool
Cjian/build.py
Cjian/build.py-cleanup
Cjian/capi-gpu
Cjian/capi-no
Cjian/cg
Cjian/ci-doc
Cjian/clean-dockerfile
Cjian/cmake
Cjian/conv_fp16
Cjian/conv-int-u8s8
Cjian/cpu-build
Cjian/cuda_pip
Cjian/cuda12_merge_mainb
Cjian/cuda12_pipeline
Cjian/cuda-12-doc
Cjian/dep_date
Cjian/disable_web_ci
Cjian/dml-ng
Cjian/doc-ci
Cjian/drop_extra
Cjian/eigen339
Cjian/ep-name
Cjian/fix_py_packing_ci
Cjian/fix_rocm_python
Cjian/fix_1es
Cjian/fused_conv
Cjian/github_issue_15093
Cjian/github-win-build-ci
Cjian/glob8
Cjian/gradle
Cjian/gradle-with-npm
Cjian/iconv_mac
Cjian/if_path
Cjian/java_cuda12
Cjian/jdk17-js
Cjian/left_over_braces
Cjian/linux_c++20
Cjian/mac_os_ci_dividsion
Cjian/mac-os-codeql
Cjian/manylinux_2014
Cjian/nodejs_linux
Cjian/npm-cg
Cjian/post_merge_wasm_testing
Cjian/postmerge_webgpu
Cjian/pydml_test
Cjian/pytest
Cjian/pytoml
Cjian/rearrange_RN_CI
Cjian/rm-cuda-pkg
Cjian/rn-0.69.1
Cjian/rust_ci
Cjian/sp2
Cjian/transformers
Cjian/try_to_fix_ctest_timeout
Cjian/vcpkg
Cjian/vs2022_c
Cjian/web_ci_2
Cjian/whisper
Cjian/win_c++20
Cjian/win-cpu-for-gpu
Cjian/windows_c++20
Cjian/1espt
ClientAML
ComplianceMac2Build
CpuOmpNuget
CudaBuildFix
CudaConvReluFix
CudaConvReluHipify
CudaConvReluLinux
CudaConvReluObs
CudaOpAPItest
CudaOpAPItestII
CudaProfilerBuild
CudaProfilerDebug111
CudaProfilerII
CudaProfilerIICuda111Build
CudaProfilerMem
CustomOPGpuBuild
CustomOpVariadicInput
CustomOpVariedInput
CustomOpVariedInput3
DS_custom_layernorm
DebugCudaKernelCreation
DebugCudaKernelCreation2
DebugFluencePrecision
DebugMobilenet
DebugMobilenet2
DebugTrainingGPU
DefaultLoggerExcept
DmlDev
DmlPrototype
DmlPrototype-1_14_1
DmlPrototype-2023_10_02
DmlPrototype-2023_11_8
DmlPrototype-Outdated
DmlPrototypeCopy
DynamicBlockBase4
DynamicBlockBaseDefault2
DynamicBlockBaseException
DynamicBlockBaseX86
DynamicBlockSize
ExprimentMaxPool
ExprimentMaxPool2
ExternalTP
FirstBranch
FixCuptiPathTestPath
FixFusedConv
FixGILDeadlockWithPythonRunAsync
FixPEwinGPU
FixRandConvBuild
FixReusePlan
GHIssue
HybridInference
IdentitySeqGPUFixBuildErr
ImplementSplitToSequenceOp
IntegratePThread
IntegratePThread2
IntegratePThread3
Jetson-arm64-CI
Jetson-arm64-CI-tag-v1.2.0
LockFreeQueue
MasterNoSpin
MasterOMP
NanInvestigate
NugetPackagingNoOMP_rename
ORT_Web_Native_MemOpt
ORTWeb_EM313_Mem_Profile
OptimizeMaxPool
PE_event_pool
PE-threading
ParallelDispatch
ParallelDispatchBiggerBlocks
ParallelDispatchBiggerBlocksReduceAtomic
ParallelDispatchExt
ParallelDispatchExtMergeExp
ParallelDispatchExtMergePy38
ParallelDispatchExtMergeSticky
ParallelDispatchNoLC
ParallelMlas
ProfileConcurrentCudaKernelBuild
ProfileTP
ProfileTP2
ProfileTP3
ProfileTP5
ProfileTP6
ProfileTP7
ProifleTP5
QAtttest
ReduceBinarySize
ReduceBinarySizeTestPipelineCopy
RefactorExecutor
RefactorSequentialExecutor
RemoveStrlen
RenameNugetPipeline
RenameNugetPipeline2
SequenceGPUMemcpy
SequentialPooling
SerializePooling
ShareProfilerBuild
TestDebBinding
TestNugetBuild
ThreadPoolLite
ThreadPoolLite2
ThreadPoolLite3
ThreadPoolProfiler
ThreadPoolProfiler2Build
ThreadPoolProfiler2Build2
ThreadPoolProfiler2Build3
ThreadPoolProfiler2Debug
ThreadPoolProfiler2Debug2
ThreadPoolProfiler2Debug3
ThreadPoolProfiler2Debug4
ThreadPoolProfiler2Debug5
ThreadPoolProfiler2Debug6
TryOutMoodyQueue
TuneHybridThreading
UpdateOpVersion
Vish/beam_search_prefix_mask
Vish/beam_search_prefix_matching
Vish/beamsearch_customop
Vish/beamsearchop_dw
Vish/beamsearchop_update1
Vish/benchmarktool
Vish/gpt_beam_search_op_copy
Vish/optimizer_attn_qkv_update
Vish/prefixmatch
Vish/pyenvupdate
Vish/qkv_output_testing
Vish/tnlrv4_opt_cuda
WAIdev
WinCuda102Pipeline
WindowsAI
abjindal/add_split_quickgelu_fusion
abjindal/deepspeed_stage3_add_fp16_optimizer
abjindal/eager_fix_win_pipeline
abjindal/eager_mode_ubuntu
abjindal/eager_windows_build
abjindal/eager_windows_ci
abjindal/fix_win_pipeline
abjindal/stage3_deepspeed_broadcast_patch
abjindal/update_training_cuda12_pipeline
abudup/rocm_profiler_deadlock_fix
aciddelgad/fix_rotary_gqa_dim_1
aciddelgado/cutlass_update
aciddelgado/cutlass_upgrade
aciddelgado/deprecate_total_seqlen
aciddelgado/fix_rotary_gqa
aciddelgado/flash_bnsh
aciddelgado/gqa_bnsh
aciddelgado/gqa_memeff
aciddelgado/gqa_rotary_packed
aciddelgado/gqa_rotary
aciddelgado/gqa_seqlens_k_left_padding
aciddelgado/memeff_disable_local
aciddelgado/mha_check_continuous
aciddelgado/single_use_gqa
aciddelgado/split_kv
aciddelgado/splitkv_mha
aciddelgado/update_neural_speed
acl_edits
adamlouly/add_bf16_gatherelementsgrad
adamlouly/add_onnxblock_big_models_support
adamlouly/expose_param_python_bindings
adamlouly/fix_directml
adamlouly/fix_inf_handling
adamlouly/fix_nighlty_pipeline
adamlouly/fix_nightly_ort_pipeline
adamlouly/investigate_sparsity_tests
adamlouly/ortmodule_pp
adamlouly/remove_unused_var_greedy_search
adamlouly/subgraph_parallel_training
add_dropout_unittest
add_grouped_gemm
add_session_to_profiler
add_tensorToDataURL
add-cuda-kernels-pad-convtranspose-opset-19-23
add-qnpu-sample
adk9/ortmodule-options-api
adrastogi/compile-telemetry
adrastogi/copilot-instructions
adrial/rel-1.22.2/cherrypick-experiment-1
adrianl/CompileApi_OrtModelInput_StreamWriteOutput
adrianl/KernelPluginEp_KernelInfoApis
adrianl/SessionQueryPartitionInfo_Revival
adrianl/SessionQueryPartitionInfo
adrianl/bug-pad-no-dq-inputs
adrianl/compile-api-ep-ctx-binary-stream
adrianl/csharp-GetCompileApi-NetStandard2
adrianl/cuda-profiler-test-failure
adrianl/ep-abi-ep-context-nodes-v2
adrianl/ep-abi-model-compilation-state
adrianl/ep-abi-qdq-utils
adrianl/experiment_optimizers
adrianl/openvino_unreachable_code
adrianl/plugin-ep-kernel-prepack
adrianl/plugin-ep-with-original-append-ep-api
adrianl/qnn-gelu-fusion-experiment
adrianl/rel-1.23.0/cherrypick-in-memory-ref-fix
adrianl/rel-1.23.1-cherrypick-1
adrianl/rel-1.23.1-update-version
adrianl/transpose-optimizer-const-folding-reuse-initializers
ads_amd
ads_1.5.1_a100_with_convgrad
adtsai/dml_ep_perf
adtsai/int8-resize
adtsai/phase2-dev
ajindal1-patch-1
alejandro/fusion
alejandro/quant_tool
amx
android_coverage_dashboard_wip
asg-main-240326
asg-ps-3.2.2
asg-w1
asg-w2
ashritms/main2win-ort-main-250116
askhade/CSharp_updates_for_trianing
askhade/enable_winml_models
askhade/fix_nuget_bug
askhade/fluency_opt
askhade/onnx_1_9
askhade/orttraining_test_updates
askhade/quantization_and_caliberation
askhade/update_onnx_tests
askhade/update_onnx-tensorrt
askhade/webt
asonawane/attention-nuance
asonawane/cherry-pick
asonawane/ct
asonawane/layoutxlm
asonawane/nuance
asonawane/position_embed
asonawane/qmoe
asonawane/qmoe-fix
asonawane/update
asonawane/xlm-commit-1
attn_bias
audupa/profile_explorer_improvements
auto_pad
babuang/stateless_graph
baijumeswani/enable-win-arm64-webgpu
baijumeswani/fl
baijumeswani/load-cuda-provider
baijumeswani/paged-attention
baijumeswani/rel-1.22.0
baijumeswani/rel-1.23.0-webgpu
baijumeswani/rel-1.23.1
baijumeswani/rel-1.23.2
baijumeswani/1230-skip-macos
bench-compute-softmax
bert_loss_convergence_baseline
bert_qdq_trt
better_diagnostics
bfloat16_cpu_support
bitnet
bowbao/bart_export
bowbao/onnx_t5
bowbao/relax_subgraph_shape_inference
broken_whisper
bug_fix_rand_input
build_python_38
c_charp_cuda
c_sharp_cuda
c_sharp_tensorrt
c-api-test-package
calibration_reduce_minmax_operator
calibration_reduce_operator
carzh/bitnet-lut
carzh/bitnet-lut-2
carzh/bitnet-lut-compute
carzh/bitnet-reverse-last-commit
carzh/bitnet-reverse-last-commit-new
carzh/bitnet-test
carzh/browserstack-ado
carzh/browserstack-android-test
carzh/browserstack-apple-test
carzh/chroma-coreml
carzh/coreml_expand
carzh/coreml-dev-after-gather
carzh/coreml-equal
carzh/coreml-equal-after-reshape
carzh/coreml-reshape-dev
carzh/coreml-test
carzh/coreml-where
carzh/nuget-test-timeout
carzh/reshape-test
carzh/run-browserstack-sample
carzh/tmac-bitnet
carzh/tmac-bitnet-fresh
check_null
checkSlpitFused
chenta/async_memcpy
chenta/bfc_arena
chenta/bfloat16_update
chenta/bfloat16
chenta/ci_test
chenta/code_style
chenta/compliance_fix
chenta/deconstruction_test
chenta/dml_transformer
chenta/eager_mkl_fix
chenta/eager_print_test
chenta/eager_prototype
chenta/eager_test
chenta/fix_cmments_3
chenta/fix_comments_and_ci
chenta/fix_comments
chenta/fix_comments_2
chenta/fix_eager_pytorch_latest
chenta/fix_gemm8_security_issue
chenta/fix_ortmodule_tensor_api
chenta/fix_thread_local
chenta/fix_training_build
chenta/gemm_tmp
chenta/graph_refactory
chenta/invoke_python
chenta/linux_runtime_path
chenta/lite_ep
chenta/multi-stream-executor
chenta/onnx_frontend
chenta/optinal
chenta/pipeline_test
chenta/process_group
chenta/pybind_load_dll
chenta/rebase_to_master
chenta/refactor_executor
chenta/revert_stream_pool
chenta/rnn_default
chenta/rnn_investigation
chenta/script_module_test
chenta/session_level_stream_pool
chenta/shard_onnx_model
chenta/skip_overlap_value_info
chenta/stride_tensor_eager
chenta/temp_fix_for_cnn
chenta/test_athena
chenta/test_barrier
chenta/test_crash
chenta/test_eager_pipeline
chenta/test_merge
chenta/test_pipelne
chenta/test_single_stream
chenta/test_stream
chenta/test_transpose
chenta/test_unified_stream
chenta/test
chenta/thread_local_test
chenta/tmp_expr
chenta/tmp_fix
chenta/tmp
chenta/training_tmp
chenta/try_hack
chenta/tvm_ep_fix
chenta/winml_fix
cherry-pick-round1-final-test
cheta/fix_executor
chi/add_external_stream_unit_test_2
chi/add_i_gpu_allocator_for_trt
chi/add_load_external_weight_as_ort_in_provider_bridge
chi/add_trt_op_types_to_exclude
chi/add_trt_rtx_pipelines
chi/c_api_graph_getsbubgraph
chi/c_api_graph_getsubgraph
chi/control_flow_op_trt_fix
chi/csharp_ortenv_logging_verbose
chi/csharp_test_code
chi/custom_op_for_ep
chi/decouple_cuda_allocator
chi/dequantize_dq_node
chi/dla_ep
chi/ep_abi_impl
chi/ep_abi_update
chi/ep_context_for_partitions
chi/fix_get_subgraph_for_trt_unit_test
chi/graph_api_add
chi/graph_get_subgraph
chi/l2_plus_opt_qdq_stripping
chi/map_to_4d_tensor
chi/mem_leak_fix
chi/no_igpuasyncallocator_workaround_with_scatternd_workaround
chi/onnx_test_runner_for_plugin_ep
chi/onnx_test_runner_for_plugin_ep_2
chi/onnx_test_runner_plugin_ep
chi/ort_graph_api_add
chi/out_of_tree_prototype
chi/outOfTreeEP
chi/per_thread_context_refactor_2
chi/plugin_trt_ep_impl
chi/reduce_size
chi/refactor_filtered_node_list
chi/rel-1.12.1
chi/revert
chi/tensorrt-8.5ea
chi/text
chi/trt_add_common_utilis
chi/trt_cuda_graph_fix
chi/trt_engine_override
chi/trt_enqueue_v3_no_dds
chi/trt_enqueue_v3
chi/trt_explict_profile_shapes
chi/trt_filtered_tests
chi/trt_multiple_profiles
chi/trt_nested_control_flow_op
chi/trt_per_thread_context_fix_bug
chi/trt_timing_cache
chi/trt_workaround_scatternd
chi/trt10-dev
chi/update_graph_view_api
chi/weightless_ep_context
chilo/trt_hash_filename
chilo-rel-1.9.1
chilo-trt-8.2-ea
codego/tcdev
codemzs/dropout12_tests
compute_only
concat_grad_fix
convsym
convsym_2x8x8
copilot/add-support-for-visual-studio-2026
copilot/fix-16449
copilot/fix-16619
copilot/fix-16998
copilot/fix-18355
copilot/fix-21661
copilot/fix-24522
copilot/fix-24538
copilot/fix-24876
copilot/fix-24880
copilot/fix-24964-2
copilot/fix-24964
copilot/fix-24965
copilot/fix-25053
copilot/fix-25644
copilot/fix-25899
copilot/fix-6139735e-a8d2-4a61-ab75-6e2e4ff92c66
copilot/fix-a31af0b5-c987-4066-a146-57018d4c24d6
copilot/fix-c23b6656-ddef-405f-8be5-8293ecafec1e
copilot/fix-d2a48cd6-d601-4da5-99cd-898d4fdcec15
copilot/fix-ead87e86-90de-4e39-9169-517c0f520567
copilot/fix-ec4062c8-bab0-447f-9177-fc7e56831d3e
copilot/fix-fd300e06-5f9a-4df0-8b2b-156af3e77f93
copilot/implement-begin-and-end-for-int64s
copilot/sub-pr-26445
copilot/sub-pr-26602-again
copilot/vscode1758837089623
copy_kv_cache
cpick_rel10
create_alloc
cuda10LinuxPy
cuda128
cudaPythonBugFix
cudaResize
cudaopt
custom_op_fix
daxing_bitnet
dense121_v
dependabot/github_actions/actions/cache-5
dependabot/github_actions/actions/download-artifact-7
dependabot/github_actions/actions/upload-artifact-6
dependabot/github_actions/github/codeql-action-4
dependabot/github_actions/reviewdog/action-shellcheck-1.32.0
dependabot/nuget/csharp/sample/Microsoft.ML.OnnxRuntime.FasterRcnnSample/SixLabors.ImageSharp-2.1.11
dependabot/nuget/csharp/sample/Microsoft.ML.OnnxRuntime.ResNet50v2Sample/SixLabors.ImageSharp-2.1.10
dependabot/pip/clang-format-21.1.7
dependabot/pip/lintrunner-adapters-0.12.6
dependabot/pip/onnxruntime/python/tools/transformers/models/llama/protobuf-4.25.8
dependabot/pip/onnxruntime/python/tools/transformers/models/llama/transformers-4.53.0
dependabot/pip/onnxruntime/python/tools/transformers/models/stable_diffusion/requirements/protobuf-4.25.8
dependabot/pip/onnxruntime/python/tools/transformers/models/stable_diffusion/requirements/transformers-4.53.0
dependabot/pip/onnxruntime/python/tools/transformers/models/whisper/protobuf-4.25.8
dependabot/pip/onnxruntime/python/tools/transformers/models/whisper/transformers-4.53.0
dependabot/pip/ruff-0.14.9
dependabot/pip/tools/ci_build/requirements/transformers-test/transformers-4.53.0
deprecate_trainabledropout
deprecation_warning
derdeljan/asg_attention_scores_buffer
derdeljan/asg_rel_123
derdeljan/asg_16bit_gqa
derdeljan/asg_123_experimental
derdeljan/hybrid_fp16_gqa
derdeljan/mla_prototype
derdeljan/optimize_16bit_gqa
derdeljan/ort_123_caching
derdeljan/ps-ort-gqa-tree-decoding
derdeljan/ps-ort-gqa-tree-decoding-2
derdeljan/softmax-add-bias-redcuce-max
detached
dev/emarin/cherry_pick_pipeline_change
dev/emarin/fix_pipeline_2
dev/emarin/rel_patch
dev/erscor/2025/12/8-try-fix-packaging
dev/kvadsariya/EPFix
dev/kvadsariya/migraphx_generic
dev/kvadsariya/ort_1.22_rel
dev/liwchang/shahasad/negative-axis-for-reduce-ops-citest
dev/opencl
dev/opencl-no-merge
dev/ryoto/cpu-trace-execution
dev/ryoto/expose_optimized_model_filepath
dev/sawidder/zcode_training
dev/shahasad/add-opset-9-10-tests-to-csharp-citest
dev/shahasad/cherry-pick-ort-server-changes-for-patch-release
dev/shahasad/cleanup-python-api-gaps-citest
dev/shahasad/conditionally-export-execution-provider-apis-in-chsarp-citest
dev/shahasad/csharp-api-and-test-for-custom-op-dll-citest
dev/shahasad/daquexian-android-ci
dev/shahasad/disable-pretrained-model-tests-in-csharp-temporarily
dev/shahasad/document-operator-providers-3
dev/shahasad/fix-android-ci
dev/shahasad/fix-azcopy-path-citest
dev/shahasad/fix-csharp-project-dependency-in-cmake
dev/shahasad/fix-csharp-run-method-interop
dev/shahasad/fix-nuget-ci-for-custom-op-dll-loading-failure
dev/shahasad/java-api-pr
dev/shahasad/java-api-pr-5
dev/shahasad/java-api-pr-6
dev/shahasad/jd-daquexian-java-api
dev/shahasad/make-a-windows-only-signed-nuget
dev/shahasad/move-systems-numerics-tensors-to-onnxruntime
dev/shahasad/move-systems-numerics-tensors-to-onnxruntime-single-assembly-citest
dev/shahasad/negative-axis-for-reduce-ops-citest
dev/shahasad/rel-0.5.1-citest
dev/shahasad/rel-1.1.0
dev/shahasad/revert-c-api-marshalling-change-for-test
dev/shahasad/setup-java-ci-windows
dev/shahasad/update-csharp-api-doc
dev/update-vcpkg-2025.07.25
dev/update-vcpkg-2025.08.27
dev/wonchung/migraphx_vendorid
dev-max-debug
dev-stick-2-py38
dev-sticky-3-build
devdiv/bart
dgx2_perf
disable-ort-external-tests-draft
dist_inf
distributed_inference
div_float16
dj/rust-ci-fix
dla_graph_transforms_need_rework
dla_graph_transforms
dnnl_fix
dnnl_fix2
dockerCheck2
docs/kernel-registry-architecture
drings/test
duli/cuda_default_stream
duli/defnullptr
duli/disable_avx2
duli/mish
duli/pybind_fix
dummy5
eager_mode
edgchen1/DataTypesBinarySizeReductions_experiment_2
edgchen1/additional_binary_size_checks
edgchen1/android_ci_multi_job
edgchen1/android_custom_build_env_option
edgchen1/arm64_mac_build_update
edgchen1/arm64_q4gemm_wip
edgchen1/binary_artifact_792db33f
edgchen1/binary_artifact_97659495
edgchen1/binary_size_check_baseline_original
edgchen1/binary_size_check_baseline
edgchen1/binary_size_check_updated_kleidiai_original
edgchen1/binary_size_check_updated_kleidiai
edgchen1/binary_size_checks_update_fix
edgchen1/binary_size_investigation
edgchen1/binsize_base
edgchen1/binsize_remove_assign_nodes_to_eps_from_minimal_build
edgchen1/binsize_remove_location_from_macros
edgchen1/binsize_trim_file_to_basename_in_macros
edgchen1/build_py_update
edgchen1/check_binsize
edgchen1/clean_training_linux_ci_machines
edgchen1/consolidate_tensor_elem_type_helpers_fix
edgchen1/conversion_script_runtime_opt_update
edgchen1/coreml_shape_related_ops_fix
edgchen1/coreml_slice_op
edgchen1/debug_cpuinfo_link_issue
edgchen1/debug_test_failure
edgchen1/detox_screenshot
edgchen1/device_discovery_fix
edgchen1/docker_login
edgchen1/dynamic_quantize_matmul_b_zp_check_fix
edgchen1/edch_test_build
edgchen1/enable_coreml_in_arm64_mac_ci
edgchen1/env_misuse_error_message
edgchen1/ep_get_kernel_registry_thread_safety_fix
edgchen1/exclude_qnbitgemm_impl_in_reduced_ops_build_fix
edgchen1/fix_binary_size_check_upload
edgchen1/fix_builds_fix
edgchen1/fix_ios_ci
edgchen1/fix_mac_build_issues_fix
edgchen1/fix_minimal_build_windows
edgchen1/fix_neon_sqnbitgemm
edgchen1/fix_rust_ci_yml
edgchen1/graph_refactor
edgchen1/gsl_baseline
edgchen1/gsl_update_lite
edgchen1/gsl_update_ms_fix
edgchen1/helper_script_update
edgchen1/ios_ci_downgrade_to_macos_12
edgchen1/ios_packaging_pipeline_update
edgchen1/ios_packaging_use_cmake_3
edgchen1/ios_packaging
edgchen1/ios_test
edgchen1/ios_training_package_fix
edgchen1/ios_xcode_15.2
edgchen1/java_api_qnn_ep_fix
edgchen1/kleidiai_bisect
edgchen1/kleidiai_sme
edgchen1/mac_arm_ci
edgchen1/memcpy_op_support_for_plugin_eps_fix
edgchen1/mlas_is_dynamic_qgemm_available_fix
edgchen1/mobile_doc_update
edgchen1/nnapi_matmul_update_fully_connected
edgchen1/nnapi_matmul_update
edgchen1/node_unit_refactor
edgchen1/nodiscard_status_fix
edgchen1/objc_api_fix
edgchen1/objc_pod_initial_release
edgchen1/perf_bisect
edgchen1/perf_test_logging
edgchen1/plugin_ep_android_fix
edgchen1/plugin_ep_unit_tests_fix
edgchen1/qnn_allocator_no_header
edgchen1/qnn_backend_mgr_clean_up_fix
edgchen1/qnn_backend_mgr_clean_up
edgchen1/qnn_ep_profiler
edgchen1/qnn_experiment
edgchen1/qnn_shmem_experiment
edgchen1/qnn_test_logging
edgchen1/qnpu
edgchen1/remove_duplicate_header
edgchen1/rn_ci_debug
edgchen1/rn_ci_investigation
edgchen1/rn_remove_package_from_android_manifest
edgchen1/sat_runtime_optimization_save_fix
edgchen1/show_ep_devices
edgchen1/split_support_more_types_fix
edgchen1/sqnbitgemm_multi_row_fix
edgchen1/sqnbitgemm_multiblock_fix
edgchen1/sqnbitgemm_precompute_zp_term
edgchen1/sqnbitgemm_quantize_a_fix
edgchen1/sqnbitgemm_quantize_a_fix_2
edgchen1/static_kernel_update_fix
edgchen1/test_build_def
edgchen1/test_feature_branch
edgchen1/test_java_coreml
edgchen1/test_ndk21
edgchen1/test_rn_ci
edgchen1/test_skip_custom_registries
edgchen1/test_win_arm_fp16
edgchen1/tvm_ep_ci_update
edgchen1/tvm_ep_ci
edgchen1/update_append_ep_docs
edgchen1/update_cpuinfo_and_windows_arm_feature_checks_fix
edgchen1/update_cpuinfo_and_windows_arm_feature_checks
edgchen1/update_doc
edgchen1/update_gradle_version_fix
edgchen1/update_mac_agents_fix
edgchen1/update_mac_agents
edgchen1/update_rn_ios_ci_fix
edgchen1/use_xcode_in_mac_ci_build_fix
edgchen1/ut_verbose_log_fix
edgchen1/xcode_investigation
edgchen1/xcode_13_1_test
edgchen1/xcode_14_3_test
edgchen1/1.11.1_for_ios_9.2
edge_telemetry
emarin/rel1.21/cherry_pick_1_qnn
emarin/rel1.21/cherry_pick_2_tensorRT
emarin/rel1.21/cherry_pick_3_ovep
emarin/rel1.21/cherry_pick_4_external_deps
enable_opt
enableCustomOpCApiTest
end_profiling
enhance_graph_viewer_to_proto
ep-validation-tool
ettao/chatT
ettao/chitchat-perf
ettao/sampling-op
experimental/VulkanEP/NCNN_POC
experimental/opencl
extend
external_tp_rel-1.10.0
fa_decode
fa_gen_opt
fajin/dqmatmultensorprotohack
fajin/dqmatmulutrefactor
fajin/matmul8bits_arm
fajin/mmnbfp16api
fajin/mmnbfp16armsimd
fajin/mmnbfp16citest
fajin/mmnbfp16citest2
fajin/qdqmatmulnbits
fdwr-patch-1
federated_learning_utils
find_intel_bug
fix_cuda_include_files
fix_etw_build
fix_graph_viewer_to_proto
fix/kleidiai-sme2-check
fix_nvcc_error_due_to_strict_aliasing_wip
fix-profiler-test
fixBuild
fixCudaDml
fixDmlTypo
fixGetTensorShapeElementCount
fixModelProtoCopy
fixNuget
fixdmlcuda2
fixopset18reduceopstransposeopt
fl-0.6.0
flash_v2_no_cuda52
flash_v2_no_cuda52_60_61
flash_v2
foundry_models_page
frdong/phi-2.5
frdong/pre-pack
frdong/prepack_test
frdong/prepack_2
frdong/tnlgv4_gs
frdong/tnlgv4
fs-eire/allow-dump-test-zip
fs-eire/allow-run-webgpu-on-node
fs-eire/allow-set-config-entry-test-runner
fs-eire/api-refactor-ort_env_webgpu
fs-eire/buffer-upload
fs-eire/cherry-pick-1.17.1
fs-eire/compatible-esm-webpack
fs-eire/concat-fix-simple-assumption
fs-eire/d
fs-eire/dawn-upgrade_test_mac_x64
fs-eire/dawn-upgrade-20250807-debug
fs-eire/debug-nodejs-options
fs-eire/debug-strict-aliasing
fs-eire/delay-load-test-debug
fs-eire/delay-load-workaround
fs-eire/dg3
fs-eire/disable-vcpkg-for-wasm-build-temporarily
fs-eire/dl
fs-eire/dml-dir
fs-eire/dump-gpu-data
fs-eire/dump-karma-debug-logs
fs-eire/emsdk_upgrade_test
fs-eire/emsdk-3.1.74_min
fs-eire/emsdk-3.1.74
fs-eire/emsdk-4.0.1
fs-eire/emsdk-upgrade-4.0.10
fs-eire/enable-c++-20-win-test
fs-eire/enable-c++20-win
fs-eire/export-test
fs-eire/expose-backend-name-in-session-creation
fs-eire/f-ci-pipe
fs-eire/fix-format
fs-eire/fix-onnxruntime-test-all-on-browsers
fs-eire/fix-ort-logging-utf8
fs-eire/fix-reduce
fs-eire/fix-test-case-asin-vulkan
fs-eire/gh-pages-doc-webgpu
fs-eire/install-cocoapods-react-native-ci
fs-eire/instance-norm_fp16_abs_error
fs-eire/io-binding-debug
fs-eire/js-ep
fs-eire/js-rn-support-android-load-model-from-buffer
fs-eire/jsep-bias
fs-eire/jspi-integrate
fs-eire/linux-webgpu-ci-debug
fs-eire/mac-arm64-enable-tests
fs-eire/mac-webgpu-pipeline-sep
fs-eire/memory-stats
fs-eire/merge-mac-webgpu-pipeline
fs-eire/minimal-repro-test-failure
fs-eire/new-indices-helper-i32
fs-eire/npm-audit-fix/cross-spawn
fs-eire/optimize-emscripten-interop-buffer
fs-eire/ort-web-es6
fs-eire/postmerge-webgpu
fs-eire/profiling-config
fs-eire/py-packaging-install-nodejs
fs-eire/qnn_fixes
fs-eire/re-enable-test-gh15949-webgpu
fs-eire/refactor-init-and-proxy
fs-eire/remove-has-deprecated-literal-operator
fs-eire/remove-unused-pipelines
fs-eire/revert-emsdk-4.0.3-upgrade
fs-eire/size-base
fs-eire/small-fixes
fs-eire/string-template-prototype-debug
fs-eire/test-initializer-alloc-reserve
fs-eire/test-mac-cross-compile
fs-eire/test-mac-with-error
fs-eire/test-triggering
fs-eire/try-fix-conv-cache-key
fs-eire/try-fix-npm-packaging-pipeline
fs-eire/try-fix-npm-packaging-pipeline-2
fs-eire/try-fix-use-dotnet
fs-eire/up_header_debug
fs-eire/upgrade-emsdk-4.0.9
fs-eire/upgrade-mac-image
fs-eire/upgrade-npm
fs-eire/use-jspi-based-asyncify
fs-eire/use-pre-downloaded-testdata-in-image-debug-no-cache
fs-eire/utils
fs-eire/w
fs-eire/w00
fs-eire/w1
fs-eire/w2
fs-eire/w3
fs-eire/w5
fs-eire/w7
fs-eire/w8
fs-eire/w74
fs-eire/w401
fs-eire/w403-dev
fs-eire/w403
fs-eire/w404
fs-eire/w-exp
fs-eire/w-old
fs-eire/w-webgpu
fs-eire/wasm-ci-webgpu-ep_debug
fs-eire/wasm-es6-test
fs-eire/wasm-webgpu-ep
fs-eire/web-ci-verbose-log
fs-eire/web-env-stat
fs-eire/web-remove-export-node-restriction-2
fs-eire/web-test-diagnose-2
fs-eire/web-test-use-chrome
fs-eire/webgpu_gqa_test
fs-eire/webgpu-allow-set-device
fs-eire/webgpu-dll
fs-eire/webgpu-dll-1
fs-eire/webgpu-ep
fs-eire/webgpu-ep-api
fs-eire/webgpu-ep-api-working
fs-eire/webgpu-ep-dawn-ext-test
fs-eire/webgpu-ep-expand
fs-eire/webgpu-ep-fix-broadcast
fs-eire/webgpu-ep-m
fs-eire/webgpu-ep-mac
fs-eire/webgpu-ep-test
fs-eire/webgpu-ep-win-test
fs-eire/webgpu-more-validation
fs-eire/webgpu-poc
fs-eire/wu
fs-eire/ww
fs-eire/2025-11-21_npm_audit_fix_js
ft_custom_op_backup
function_body
ganik/mse
gemini/test-windows-qnn-workflow
gemini-cherry-pick-1.23.0
genai_sectionsix
gh/garymm/2/orig
gh/justinchuby/1/base
gh/justinchuby/1/orig
gh/justinchuby/2/base
gh/justinchuby/2/orig
gh-pages
gh-pages-cuda-profiling
gh-pages-pr
gh-pages-pr-c-docs
gh-pages-pr-csharp-docs
gh-pages-pr-python-docs
gh-paghe
gpt_main_test
gpt2_script
gpu_tarball_zipfile_test
gqa_attention
gqa_seqlens_k
grad_bcast_fix
gs/sigmoidmul
gs/wip
gt/kedeng/BertCpuOpt-omp
gt/kedeng/BertCpuOpt-omp-ablate
guangyunhan/ck-convert-bias-mask
guangyunhan/clip-relu-quant-fusion-l1
guangyunhan/clip-relu-removal
guangyunhan/decoding-for-amd-e2e
guangyunhan/exp-fused-gemms
guangyunhan/fallback-cuda-to-rocm
guangyunhan/fix-cuda-530-test
guangyunhan/fix-eigen
guangyunhan/fp8-gemm-bias
guangyunhan/fp8-gemm-new-ck
guangyunhan/fused-gemms-flash-attention-instances
guangyunhan/ke-skip-vendor-libraries
guangyunhan/main
guangyunhan/memcpy-infer-output-memtype
guangyunhan/opencl-fence
guangyunhan/paged
guangyunhan/qdq-stripping-option
guangyunhan/qnn-clip-relu-removal
guangyunhan/qnn-clip-relu-removal-test
guangyunhan/refactor-ke-register2
guangyunhan/rocm-image-add-dotnet
guangyunhan/roctx
guangyunhan/shape-aware-allocation
guangyunhan/update-rocm-test
gwang-msft/AddSupportForXamarinToCSharp
gwang-msft/AddSupportForXamarinToCSharp2
gwang-msft/android_app_center_test
gwang-msft/cleanup_c_api
gwang-msft/coreml_ep_v0-log-sink
gwang-msft/coreml_python_api
gwang-msft/fix_traing_distributed_ci_failure
gwang-msft/improve_android_test
gwang-msft/ios_app_center
gwang-msft/ios_build_sign
gwang-msft/ios_build_update
gwang-msft/ios_build
gwang-msft/ios_ci
gwang-msft/ios_coreml_test
gwang-msft/ios_model_runner
gwang-msft/ios_package_test
gwang-msft/mbnt_v2_test
gwang-msft/mbnt_v2_test_1
gwang-msft/nnapi_build_settings_test
gwang-msft/nnapi_minimal_ci
gwang-msft/nnapi_minor_fix
fix attention mask
yufenglee
committed
2 years ago
249fcc1e
comments and docs
aciddelgado
committed
2 years ago
96b02705
change seqlen logic
aciddelgado
committed
2 years ago
bcd126ae
deps update
aciddelgado
committed
2 years ago
b5b62cdc
eigen update
aciddelgado
committed
2 years ago
6d754f68
undo cmake/external/onnx change
aciddelgado
committed
2 years ago
66f1600d
docs
aciddelgado
committed
2 years ago
791621b0
address comments
aciddelgado
committed
2 years ago
2fab38e7
remove kv share flag and bnsh flag
aciddelgado
committed
2 years ago
9e2fae76
build warnings
aciddelgado
committed
2 years ago
d89995f0
fix warning and lint
aciddelgado
committed
2 years ago
e2eadab7
merge main
aciddelgado
committed
2 years ago
40f6e3b5
disable memory efficient and pipeline test
aciddelgado
committed
2 years ago
90f23c0d
[TensorRT EP] Properly set CUDA_INCLUDE_DIR for onnx-tensorrt (#18274)
chilo-ms
committed
2 years ago
Verified
dfafcb58
flash attention works no buffer
aciddelgado
committed
2 years ago
4c5a32ab
attention mask for flash attention with cache
aciddelgado
committed
2 years ago
afa8ea01
Remove internal enforce for IO binding inputs (#18266)
kunal-vaishnavi
committed
2 years ago
Verified
08eaa1c5
[TensorRT EP] Fix bug for shape tensor input (#18253)
chilo-ms
committed
2 years ago
Verified
84bdf04b
Block-wise 4b quantization matmul operator change (#18172)
chenfucn
committed
2 years ago
Verified
26b39641
Make MlasTestFixture::mlas_tester an inline variable. (#18263)
edgchen1
committed
2 years ago
Verified
2ec1f94b
Change a bitwise logical xor to logical wise (#18246)
Changming Sun
committed
2 years ago
Verified
4c4d79a6
Fix Signed Mismatch (#18258)
nums11
committed
2 years ago
Verified
192caee8
[JS/Web] Added Unifroms support to unary ops. (#18223)
satyajandhyala
committed
2 years ago
Verified
e207060a
[QNN EP] Fix Pad UT (#17982)
winskuo-quic
committed
2 years ago
Verified
90f205e7
Rework/cleanup the C# build infrastructure for nuget packages. (#18127)
skottmckay
committed
2 years ago
Verified
c352e9b1
Update XNNPACK to latest version (#18038)
skottmckay
committed
2 years ago
Verified
4f2096be
Introduce new optimizer Pad + Conv/MaxPool (#18136)
sumitsays
committed
2 years ago
Verified
e36d0037
Pre-link when creating static library for apple framework (#18241)
skottmckay
committed
2 years ago
Verified
016b7526
Partially disable QGemm tests for float 8 types (#18196)
xadupre
committed
2 years ago
Verified
1439da36
Rerun the flaky ort-web tests automatically (#18187)
mszhanyi
committed
2 years ago
Verified
9f5a6856
Older