Set up CI with Azure Pipelines - #1
Closed
azure-pipelines[bot] wants to merge 1 commit into
Closed
Conversation
|
|
tmccrmck
added a commit
to tmccrmck/onnxruntime
that referenced
this pull request
Aug 28, 2019
Simple CMake setup for ONNX hosting
groszewn
pushed a commit
to groszewn/onnxruntime
that referenced
this pull request
Nov 13, 2019
…essor_double Update TreeEnsembleRegressor type support
titaiwangms
added a commit
to titaiwangms/onnxruntime
that referenced
this pull request
May 6, 2026
Tianlei BLOCKER microsoft#1: New mode-1+softcap differentiating test (C++ + Python). With softcap > 0 active, qk_matmul_output_mode=1 (post-microsoft#7913 numbering = kPostSoftCap) snapshots softcap*tanh(scale*QK/softcap) with NO mask added. Without softcap, mode 1 aliases mode 0, so the swap is observationally indistinguishable — this test is what proves the 1<->2 swap actually changed semantics correctly. Tianlei BLOCKER microsoft#2: New softcap+nonpad_kv_seqlen leakage test (C++ + Python). Exercises the latent fix where the nonpad sentinel is now applied AFTER softcap (per onnx#7867 ordering). Pre-fix: tanh squashed the sentinel, leaking poison V at padded positions through softmax. Bot inline minors: - microsoft#3 (test_gqa.py): clarify fp16 docstring — CPU does support fp16; fp32 is the natural EP-native dtype for the canary. - microsoft#4 (attention_op_test.cc): regen comment now cites shared opset 23/24 ordering and notes RunTest4D builds at opset 23. - microsoft#5 (attention_parameters.h): typo defintion -> definition. - microsoft#6 (attention.cc): replace 'guaranteed -inf' with precise wording citing mask_filter_value<T>() = numeric_limits::lowest() / MLFloat16::MinValue sentinel and the MLAS softmax finite-input requirement (attention.h). R-2 microsoft#1 (attention_parameters.h): Spec-leading documentation block on the QKMatMulOutputMode enum noting that ORT now uses the post-onnx#7913 numbering, while the bundled cmake/external/onnx (v1.21.0) still reflects the old numbering. ORT leads the spec change pending the next bundled-ONNX bump. Plumbing: common.py attention_prompt_func gains an optional output_qk kwarg (default 0 / disabled). When > 0, returns a 4-tuple including the qk_matmul snapshot tensor; otherwise unchanged 3-tuple. No existing callers are affected. Test results: - AttentionTest.* — 60/60 PASS (was 58, +2 new). - TestONNXAttentionCPUSoftcapMaskOrdering — 4/4 PASS (was 2, +2 new). - lintrunner clean across all 5 touched files. Refs: lead-39245992/upstream-pr-status-recheck.md, pr1v2-review-{code,critical,readability,qa}.md Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
This was referenced May 8, 2026
chilo-ms
pushed a commit
that referenced
this pull request
Jun 1, 2026
### Description
Add an internal session config entry, `"session.compile_only"`, set by
`CompileModel()` before
session initialization. The NvTensorRTRTX EP reads it in
`NvExecutionProviderInfo::FromProviderOptions()` and, when set, skips
`deserializeCudaEngine()` /
`createExecutionContext()` in `CreateNodeComputeInfoFromGraph()`.
The EP context node is still saved — that path uses the serialized
engine buffer directly and does
not depend on the deserialized engine. A stub compute function is
registered to satisfy the
framework; it returns `NOT_IMPLEMENTED` if called, which cannot happen
in practice because
compile-only sessions are destroyed without inference.
### Motivation and Context
`OrtCompileAPI::CompileModel()` creates an `InferenceSession` solely to
drive `EP::Compile()` and
write out the EPContext model, then destroys it without running
inference. During that session, the
NvTensorRTRTX EP was performing a full `deserializeCudaEngine()` and
`createExecutionContext()` —
uploading engine weights to the GPU and JIT-ing the engine, only to free
everything when the session
was destroyed.
When the user then loads the EPContext model in a real session, the same
JIT and upload happen again.
Net effect on the typical "compile, then load and run" flow:
```
ONNX model
→ CompileModel() [JIT + GPU upload #1 — discarded]
→ EP context model saved to disk
→ Session from EP context model
[JIT + GPU upload #2 — necessary]
→ Inference
```
JIT and GPU upload run twice.
4 tasks
5 tasks
This was referenced Jul 22, 2026
tianleiwu
added a commit
that referenced
this pull request
Jul 27, 2026
) ### Description `import onnxruntime` segfaults during `dlopen` of `onnxruntime_pybind11_state.so` on Linux. This removes the global initializer in `onnxruntime_pybind_state.cc` that eagerly calls `Env::Default()`, and resolves the platform `Env` on first use at its two call sites instead. ### Motivation and Context The module has a namespace-scope dynamic initializer: ```cpp static Env& platform_env = Env::Default(); ``` Since POSIX telemetry landed (#27379), `Env::Default()` constructs `PosixEnv`, whose `PosixTelemetry` member initializes the 1DS SDK in its constructor. That path reads `defaultRuntimeConfig`, a namespace-scope `static ILogConfiguration` defined in the 1DS SDK's `RuntimeConfig_Default.hpp`, which lives in a **different translation unit of the same shared library**. Dynamic initialization order across translation units is unspecified, and the pybind TU's initializer runs first. `Variant::merge_map` therefore iterates a still zero-initialized `std::map`: `_M_node_count == 0`, but `_M_header._M_left` is `nullptr` rather than self-pointing, so `begin() != end()` and the loop dereferences null. Textbook static initialization order fiasco. Backtrace (Release build relinked without `--strip-all` to recover symbols): ``` #0 std::map<..., Variant>::lower_bound stl_map.h:1307 #1 std::map<..., Variant>::operator[] stl_map.h:509 #2 Variant::merge_map VariantType.hpp:508 #3 RuntimeConfig_Default::RuntimeConfig_Default RuntimeConfig_Default.hpp:97 #4 LogManagerImpl::LogManagerImpl LogManagerImpl.cpp:183 #5 LogManagerFactory::Create LogManagerFactory.cpp:36 #6 LogManagerFactory::lease #7 LogManagerFactory::Get LogManagerFactory.hpp:71 #8 LogManagerProvider::Get LogManagerProvider.cpp:16 #9 onnxruntime::PosixTelemetry::Initialize() #10 onnxruntime::PosixTelemetry::PosixTelemetry() #11 onnxruntime::(anonymous namespace)::PosixEnv::PosixEnv() #12 onnxruntime::Env::Default() #13 _GLOBAL__sub_I_onnxruntime_pybind_state.cc #14 call_init elf/dl-init.c:74 ... #21 _dl_open elf/dl-open.c:905 ``` The crash is independent of `LD_LIBRARY_PATH` and `CUDA_VISIBLE_DEVICES` — it happens before any ORT runtime code runs. `libonnxruntime.so` is unaffected because it contains no global initializer that reaches `Env::Default()`, which is why C/C++ and onnxruntime-genai consumers do not see it. Both remaining uses of `platform_env` are inside pybind lambdas that run long after load, so calling `Env::Default()` there is safe. This also removes the now-stale `TODO: we may delay-init this variable` and a pre-existing `#pragma warning(push)` that should have been `pop`. Note for follow-up: `Env::Default()` is now unsafe to call from any dynamic initializer. This was the only such call site in the tree, but hardening `PosixTelemetry` to defer SDK initialization out of its constructor would remove the hazard entirely. ### Tests Verified on a Linux CUDA 13 Release build (`onnxruntime_USE_TELEMETRY` enabled): - `dlopen` of `onnxruntime_pybind11_state.so` succeeds (previously SIGSEGV). - `import onnxruntime` reports the version and `['CUDAExecutionProvider', 'CPUExecutionProvider']`. - `onnxruntime.enable_telemetry_events()` / `disable_telemetry_events()` — the two call sites changed here — work. - CPU and CUDA inference sessions produce correct results. - Reproduced and verified with `LD_LIBRARY_PATH` unset and `CUDA_VISIBLE_DEVICES` empty.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
No description provided.