Skip to content

refact: Split executor and move hardware/error log logic for new file#26

Open
baominghelly wants to merge 2 commits intomasterfrom
refact/split_executor
Open

refact: Split executor and move hardware/error log logic for new file#26
baominghelly wants to merge 2 commits intomasterfrom
refact/split_executor

Conversation

@baominghelly
Copy link
Collaborator

Description

refact: Split executor and move hardware/error log logic for new file

Test evidence

Code check

pre-commit run --files infinimetrics/executor.py infinimetrics/common/error_handler.py infinimetrics/common/hardware_info.py 
black....................................................................Passed
flake8...................................................................Passed

Operator test

python main.py format_input_matmul.json 
2026-02-25 15:36:30,805 - infinimetrics.utils.input_loader - INFO - Loaded 1 input(s) from format_input_matmul.json
2026-02-25 15:36:30,805 - infinimetrics.dispatcher - INFO - Processing 1 valid inputs (skipped 0 invalid)
2026-02-25 15:36:32,454 - infinimetrics.dispatcher - INFO - Validation complete: 1 valid, 0 skipped
2026-02-25 15:36:32,454 - infinimetrics.dispatcher - INFO - [1/1] Executing operator.InfiniCore.Matmul.Performance
2026-02-25 15:36:32,454 - infinimetrics.executor - INFO - Executor: Running operator.InfiniCore.Matmul.Performance
2026-02-25 15:36:32,454 - infinimetrics.operators.infinicore_adapter - INFO - InfiniCoreAdapter: Processing operator.InfiniCore.Matmul.Performance
🚀 Mode: Dynamic Execution
InfiniCore Operator Test Runner
Directory: Dynamic (1 cases)
Tests found: 1

✅  test_Matmul_0: PASSED (code: 0)

============================================================
Testing Matmul on NVIDIA
============================================================
TestCase(Auto-Gen: Matmul - inputs=[in_0: tensor(2048, 2048), float16; in_1: tensor(2048, 2048), float16], kwargs={out=output: tensor(2048, 2048), float16})
    PyTorch    time - Host: 0.304630 ms, Device: 0.387913 ms
    InfiniCore time - Host: 0.305629 ms, Device: 0.327418 ms
✓ Passed

============================================================
TEST SUMMARY
Total tests: 1
Passed: 1
Success rate: 100.0%

All tests passed!
------------------------------------------------------------
BENCHMARK SUMMARY
PyTorch Host Total Time: 30.463 ms
PyTorch Device Total Time: 38.791 ms
InfiniCore Host Total Time: 30.563 ms
InfiniCore Device Total Time: 32.742 ms
Host Speedup (PyTorch/InfiniCore): 1.00x
Device Speedup (PyTorch/InfiniCore): 1.18x
============================================================
💾 Saving to: test_report_20260225_153632_868.json
   ✅ Saved.
----------------------------------------

================================================================================
CUMULATIVE TEST SUMMARY
================================================================================
Total tests run: 1
Passed: 1
Failed: 0
----------------------------------------
BENCHMARK SUMMARY (1 cases):
----------------------------------------

✅ PASSED OPERATORS (1):
  test_Matmul_0

Success rate: 100.0%

🎉 All tests passed!
2026-02-25 15:36:32,973 - infinimetrics.executor - INFO - Executor: operator.InfiniCore.Matmul.Performance completed with code=0
2026-02-25 15:36:32,974 - infinimetrics.dispatcher - INFO - Summary saved to summary_output/dispatcher_summary_20260225_153632.json

============================================================
Test Summary
============================================================
Total tests:   1
Successful:    1
Failed:        0
Success rate:  100.0%
============================================================

@baominghelly baominghelly self-assigned this Feb 25, 2026
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants