onnxruntime/onnxruntime/test
Chen Fu 4819fbf31c
Augment blockwise quantization (#18101)
### Description
Augment block wise 4b quantization -- plain CPU impl

### Motivation and Context

Allow column wise or row wise blocks. Experiments show row wise
quantization in LLM weight matrices achieves better precision.

Added tests for quantization and dequantization code.
2023-10-30 09:14:37 -07:00
..
common [C#, CPP] Introduce Float16/BFloat16 support and tests for C#, C++ (#16506) 2023-07-14 10:46:52 -07:00
contrib_ops Add MatMul FP4 and NF4 Support (#18066) 2023-10-25 15:34:58 -07:00
custom_op_registration Support custom ops taking float 8 tensors as inputs and outputs (#16323) 2023-07-06 14:36:06 +02:00
debug_node_inputs_outputs Separate out operator vs model testing. (#16228) 2023-06-17 12:58:57 +10:00
framework Functions Ahead Of Time inlininng (#17764) 2023-10-23 17:42:20 -07:00
fuzzing Run clang-format in CI (#15524) 2023-04-18 09:26:58 -07:00
global_thread_pools Allow RunAsync with global TP (#17157) 2023-08-15 14:29:10 -07:00
ir Run clang-format in CI (#15524) 2023-04-18 09:26:58 -07:00
logging_apis Run clang-format in CI (#15524) 2023-04-18 09:26:58 -07:00
mlas Augment blockwise quantization (#18101) 2023-10-30 09:14:37 -07:00
onnx GemmFloat8 as a contrib ops (#16051) 2023-10-27 14:33:55 +02:00
opaque_api Run clang-format in CI (#15524) 2023-04-18 09:26:58 -07:00
optimizer Introduce new optimizer MatMul + BatchNormalization (#17915) 2023-10-24 19:41:10 -07:00
perftest Fix regression in perf test runner (#18139) 2023-10-29 19:26:12 -07:00
platform Run clang-format in CI (#15524) 2023-04-18 09:26:58 -07:00
proto
providers Enable global TRT timing cache (#17865) 2023-10-27 09:23:19 -07:00
python Distributed Expand (#18126) 2023-10-28 00:44:02 -07:00
quantization remove AllocatorMgr class (#16509) 2023-06-28 15:43:19 -07:00
shared_lib [TensorRT EP] Add unit test for user provided cuda stream (#17974) 2023-10-23 19:41:15 -07:00
testdata Replace Transpose with Replace if they are equivalent (#18096) 2023-10-27 23:50:18 +08:00
unittest_main Enable verbose logging in unit test program with environment variable. (#17133) 2023-08-22 12:13:52 -07:00
util [DML EP] Add dynamic graph compilation (#17876) 2023-10-25 19:56:16 -07:00
wasm Enable Web CI on Linux (#16419) 2023-06-22 15:42:58 +08:00
win_getopt Run clang-format in CI (#15524) 2023-04-18 09:26:58 -07:00
xctest Enable backtrace in unit tests (#17655) 2023-09-29 12:32:56 -07:00