Skip to content

Sync with Microsoft ONNX Runtime - 03092026 #1282

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
hdharpure9922 merged 9 commits into from
Sep 3, 2026
Merged

Sync with Microsoft ONNX Runtime - 03092026 #1282

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
9 commits
Select commit Hold shift + click to select a range
a6e96aa
Validate 'num_scan_inputs' attribute in Scan kernel construction (#31…
titaiwangms Sep 1, 2026
b482740
Merge branch 'microsoft:main' into master
hdharpure9922 Sep 2, 2026
c79e932
[CUDA] Speed up low-lane int64 CumSum by up to 9.16x (#32238)
justinchuby Sep 2, 2026
3f62927
fix(ci): clone dawn via ADO mirror & github when building on ADO (#29…
sanaa-hamel-microsoft Sep 2, 2026
2a5b485
Add DeepSeek Engram contrib ops (EngramGate, NGramHashMapping) (#32268)
Copilot Sep 2, 2026
1f71c9c
[WebGPU] Expose safe graph capture I/O in Python (#32074)
4n4ny4 Sep 2, 2026
cc3da29
[WebGPU] Webgpu im2col fused activation (#32185)
4n4ny4 Sep 2, 2026
70d0b66
Merge remote-tracking branch 'upstream/main'
AIFrameworksIntegration Sep 2, 2026
b874732
Merge remote-tracking branch 'origin/master' into sync_msft_03092026
AIFrameworksIntegration Sep 2, 2026
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
7 changes: 5 additions & 2 deletions .github/workflows/lint.yml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -52,8 +52,11 @@ jobs:
- name: Setup Python
uses: actions/setup-python@ece7cb06caefa5fff74198d8649806c4678c61a1 # v6.3.0
with:
# Use the version configured in target-version of [tool.black] section in pyproject.toml.
python-version: "3.10"
# Use a version pre-installed in the runner pool's read-only tool cache; requesting an
# uncached version makes setup-python fail trying to write to /opt/hostedtoolcache.
# This is only the interpreter lintrunner runs on. The Python syntax the linters target
# is set by target-version under [tool.ruff] in pyproject.toml, independently of this.
python-version: "3.12"
- name: Setup Rust
uses: actions-rs/toolchain@16499b5e05bf2e26879000db0c1d13f7e13fa3af # v1.0.7
with:
Expand Down
3 changes: 2 additions & 1 deletion .github/workflows/pr_checks.yml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -33,7 +33,8 @@ jobs:
- name: Setup Python
uses: actions/setup-python@ece7cb06caefa5fff74198d8649806c4678c61a1 # v6.3.0
with:
python-version: "3.10"
# Keep in sync with lint.yml; must be a version cached on the runner pool.
python-version: "3.12"
- name: Setup Rust
uses: actions-rs/toolchain@16499b5e05bf2e26879000db0c1d13f7e13fa3af # v1.0.7
with:
Expand Down
9 changes: 5 additions & 4 deletions cmake/onnxruntime_providers_coreml.cmake
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -13,9 +13,9 @@ add_compile_definitions(COREML_ENABLE_MLPROGRAM=1)
if(LINUX)
find_library(LibUUID_LIBRARY NAMES uuid)
find_path(LibUUID_INCLUDE_DIR NAMES uuid/uuid.h)
if (NOT LibUUID_INCLUDE_DIR)
message(FATAL "uuid/uuid.h was not found as is required for ML Program support. "
"Run `sudo apt install uuid-dev` if you need to test ML Program related CoreML EP code. ")
if (NOT LibUUID_INCLUDE_DIR OR NOT LibUUID_LIBRARY)
message(FATAL_ERROR "libuuid (uuid/uuid.h) was not found and is required for ML Program support. "
"Run `sudo apt install uuid-dev`, or build with `--use_vcpkg` so the libuuid port is used. ")
endif()
endif()

Expand Down Expand Up @@ -194,7 +194,8 @@ target_include_directories(onnxruntime_providers_coreml PRIVATE
)

if (LINUX)
target_link_libraries(onnxruntime_providers_coreml PRIVATE uuid)
target_include_directories(onnxruntime_providers_coreml PRIVATE ${LibUUID_INCLUDE_DIR})
target_link_libraries(onnxruntime_providers_coreml PRIVATE ${LibUUID_LIBRARY})
endif()


Expand Down
8 changes: 7 additions & 1 deletion cmake/vcpkg.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -86,7 +86,13 @@
},
"coreml-ep": {
"description": "Build with CoreML EP",
"dependencies": ["fp16"]
"dependencies": [
"fp16",
{
"name": "libuuid",
"platform": "linux"
}
]
},
"dml-ep": {
"description": "Build with DirectML EP",
Expand Down
175 changes: 168 additions & 7 deletions docs/ContribOperators.md
View file
Open in desktop

Large diffs are not rendered by default.

4 changes: 4 additions & 0 deletions docs/OperatorKernels.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -582,6 +582,7 @@ The **OpSet Version** column uses the following notation:
|DynamicQuantizeMatMul|*in* A:**T1**<br> *in* B:**T2**<br> *in* b_scale:**T1**<br> *in* b_zero_point:**T2**<br> *in* bias:**T1**<br> *out* Y:**T1**|1+|**T1** = tensor(float)<br/> **T2** = tensor(int8), tensor(uint8)|
|DynamicTimeWarping|*in* input:**F**<br> *out* output:**I**|1+|**F** = tensor(float)<br/> **I** = tensor(int32)|
|EmbedLayerNormalization|*in* input_ids:**T1**<br> *in* segment_ids:**T1**<br> *in* word_embedding:**T**<br> *in* position_embedding:**T**<br> *in* segment_embedding:**T**<br> *in* gamma:**T**<br> *in* beta:**T**<br> *in* mask:**T1**<br> *in* position_ids:**T1**<br> *out* output:**T**<br> *out* mask_index:**T1**<br> *out* embedding_sum:**T**|1+|**T** = tensor(float)|
|EngramGate|*in* key:**T**<br> *in* query:**T**<br> *in* value:**T**<br> *in* key_norm_scale:**T**<br> *in* query_norm_scale:**T**<br> *out* output:**T**|1+|**T** = tensor(float), tensor(float16)|
|ExpandDims|*in* X:**T**<br> *in* axis:**tensor(int32)**<br> *out* Y:**T**|1+|**T** = tensor(bfloat16), tensor(bool), tensor(double), tensor(float), tensor(float16), tensor(int16), tensor(int32), tensor(int64), tensor(int8), tensor(string), tensor(uint16), tensor(uint32), tensor(uint64), tensor(uint8)<br/> **axis** = tensor(int32)|
|FastGelu|*in* X:**T**<br> *in* bias:**T**<br> *out* Y:**T**|1+|**T** = tensor(float)|
|FusedConv|*in* X:**T**<br> *in* W:**T**<br> *in* B:**T**<br> *in* Z:**T**<br> *out* Y:**T**|1+|**T** = tensor(float)|
Expand All @@ -608,6 +609,7 @@ The **OpSet Version** column uses the following notation:
|MoE|*in* input:**T**<br> *in* router_probs:**T**<br> *in* fc1_experts_weights:**T**<br> *in* fc1_experts_bias:**T**<br> *in* fc2_experts_weights:**T**<br> *in* fc2_experts_bias:**T**<br> *in* fc3_experts_weights:**T**<br> *in* fc3_experts_bias:**T**<br> *out* output:**T**|1+|**T** = tensor(float)|
|MultiHeadAttention|*in* query:**T**<br> *in* key:**T**<br> *in* value:**T**<br> *in* bias:**T**<br> *in* key_padding_mask:**M**<br> *in* attention_bias:**T**<br> *in* past_key:**T**<br> *in* past_value:**T**<br> *in* past_sequence_length:**M**<br> *in* cache_indirection:**M**<br> *out* output:**T**<br> *out* present_key:**T**<br> *out* present_value:**T**<br> *out* qk:**QK**|1+|**T** = tensor(float)|
|MurmurHash3|*in* X:**T1**<br> *out* Y:**T2**|1+|**T1** = tensor(double), tensor(float), tensor(int32), tensor(int64), tensor(string), tensor(uint32), tensor(uint64)<br/> **T2** = tensor(int32), tensor(uint32)|
|NGramHashMapping|*in* input_ids:**M**<br> *in* multipliers:**M**<br> *in* vocab_sizes:**M**<br> *in* past_ids:**M**<br> *out* hash_ids:**M**<br> *out* present_ids:**M**|1+|**M** = tensor(int32), tensor(int64)|
|NGramRepeatBlock|*in* input_ids:**Tid**<br> *in* scores:**T**<br> *out* scores_out:**T**|1+|**T** = tensor(float)<br/> **Tid** = tensor(int64)|
|NhwcMaxPool|*in* x:**T**<br> *out* y:**T**|1+|**T** = tensor(int8), tensor(uint8)|
|Pad|*in* data:**T**<br> *in* pads:**tensor(int64)**<br> *in* value:**T**<br> *out* output:**T**|1+|**T** = tensor(float)|
Expand Down Expand Up @@ -1087,6 +1089,7 @@ The **OpSet Version** column uses the following notation:
|DequantizeWithOrder|*in* input:**Q**<br> *in* scale_input:**S**<br> *out* output:**F**|1+|**F** = tensor(float), tensor(float16)<br/> **Q** = tensor(int8)<br/> **S** = tensor(float)|
|DynamicTimeWarping|*in* input:**F**<br> *out* output:**I**|1+|**F** = tensor(float)<br/> **I** = tensor(int32)|
|EmbedLayerNormalization|*in* input_ids:**T1**<br> *in* segment_ids:**T1**<br> *in* word_embedding:**T**<br> *in* position_embedding:**T**<br> *in* segment_embedding:**T**<br> *in* gamma:**T**<br> *in* beta:**T**<br> *in* mask:**T1**<br> *in* position_ids:**T1**<br> *out* output:**T**<br> *out* mask_index:**T1**<br> *out* embedding_sum:**T**|1+|**T** = tensor(float), tensor(float16)|
|EngramGate|*in* key:**T**<br> *in* query:**T**<br> *in* value:**T**<br> *in* key_norm_scale:**T**<br> *in* query_norm_scale:**T**<br> *out* output:**T**|1+|**T** = tensor(bfloat16), tensor(float), tensor(float16)|
|FastGelu|*in* X:**T**<br> *in* bias:**T**<br> *out* Y:**T**|1+|**T** = tensor(bfloat16), tensor(double), tensor(float), tensor(float16)|
|FusedConv|*in* X:**T**<br> *in* W:**T**<br> *in* B:**T**<br> *in* Z:**T**<br> *out* Y:**T**|1+|**T** = tensor(float)|
|FusedMatMul|*in* A:**T**<br> *in* B:**T**<br> *out* Y:**T**|1+|**T** = tensor(bfloat16), tensor(double), tensor(float), tensor(float16)|
Expand Down Expand Up @@ -1114,6 +1117,7 @@ The **OpSet Version** column uses the following notation:
|MatMulNBits|*in* A:**T1**<br> *in* B:**T2**<br> *in* scales:**T1**<br> *in* zero_points:**T3**<br> *in* g_idx:**T4**<br> *in* bias:**T1**<br> *out* Y:**T1**|1+|**T1** = tensor(bfloat16), tensor(float), tensor(float16)<br/> **T2** = tensor(uint8)<br/> **T3** = tensor(bfloat16), tensor(float), tensor(float16), tensor(uint8)|
|MoE|*in* input:**T**<br> *in* router_probs:**T**<br> *in* fc1_experts_weights:**T**<br> *in* fc1_experts_bias:**T**<br> *in* fc2_experts_weights:**T**<br> *in* fc2_experts_bias:**T**<br> *in* fc3_experts_weights:**T**<br> *in* fc3_experts_bias:**T**<br> *out* output:**T**|1+|**T** = tensor(bfloat16), tensor(float), tensor(float16)|
|MultiHeadAttention|*in* query:**T**<br> *in* key:**T**<br> *in* value:**T**<br> *in* bias:**T**<br> *in* key_padding_mask:**M**<br> *in* attention_bias:**T**<br> *in* past_key:**T**<br> *in* past_value:**T**<br> *in* past_sequence_length:**M**<br> *in* cache_indirection:**M**<br> *out* output:**T**<br> *out* present_key:**T**<br> *out* present_value:**T**<br> *out* qk:**QK**|1+|**QK** = tensor(bfloat16), tensor(float), tensor(float16)<br/> **T** = tensor(bfloat16), tensor(float), tensor(float16)|
|NGramHashMapping|*in* input_ids:**M**<br> *in* multipliers:**M**<br> *in* vocab_sizes:**M**<br> *in* past_ids:**M**<br> *out* hash_ids:**M**<br> *out* present_ids:**M**|1+|**M** = tensor(int32), tensor(int64)|
|NGramRepeatBlock|*in* input_ids:**Tid**<br> *in* scores:**T**<br> *out* scores_out:**T**|1+|**T** = tensor(float)<br/> **Tid** = tensor(int64)|
|NhwcConv|*in* X:**T**<br> *in* W:**T**<br> *in* B:**T**<br> *out* Y:**T**|1+|**T** = tensor(float), tensor(float16)|
|PackedAttention|*in* input:**T**<br> *in* weights:**T**<br> *in* bias:**T**<br> *in* token_offset:**M**<br> *in* cumulative_sequence_length:**M**<br> *in* attention_bias:**T**<br> *out* output:**T**|1+|**T** = tensor(float), tensor(float16)|
Expand Down
Loading
Loading