mirror of
https://github.com/saymrwulf/onnxruntime.git
synced 2026-05-18 21:21:17 +00:00
459c750b03
### Description <!-- Describe your changes. --> 1. Make JBLAS codes an external module of ORT. 2. Move q4 gemm code to contrib_ops. 3. Update template kernel library to v0.1 release. ### Motivation and Context <!-- - Why is this change required? What problem does it solve? - If it fixes an open issue, please link to the issue here. --> We found that the current LLM model performance is far below our expectations. Here is some performance data collected on Mistral-7B model with Xeon-8480: 8 threads | prompt length=32 past_len=32 | prompt length=1 past_len=32 -- | -- | -- ORT-main | 1220ms | 263ms Neural-speed | 564ms | 87ms ORT-this PR|597ms|120ms Although `Neural-speed` and `ORT-this PR` use the same int4 kernel code, there is a 33ms(87ms vs. 120ms) latency gap between the two frameworks. Through some statistics analysis, the summary latency of `MatMulNBits` is 86.7ms The summary latency of all int4 GEMMs in `Neural-speed` is 84.8ms. So other OPs introduce an extra 30ms latency. The performance of MatMulNBits in this PR meets our expectations. ### Remain Issues 1. For hybrid CPUs, like core 12900K, the ONNXRuntime thread pool uses TaskGranularityFactor to scale its number of threads. This is not expected in our code design. It may slow down the hybrid CPU performance by 30~40%. 2. Prepack uses a single thread which is very slow to init a session. 3. MatMulNBits with zero points will fall through to COMP_FP32 even accuracy_level=4. Our COMP_INT8 IGemmCore with zero points process is not optimized for now. It will be updated in the future. So, for an int4 model with zero points, whether the accuracy_level is 0 or 4 will be no difference. |
||
|---|---|---|
| .. | ||
| emsdk@4e2496141e | ||
| git.Win32.2.41.03.patch | ||
| libprotobuf-mutator@7a2ed51a6b | ||
| onnx@b86cc54efc | ||
| abseil-cpp.cmake | ||
| abseil-cpp.natvis | ||
| composable_kernel.cmake | ||
| cutlass.cmake | ||
| dml.cmake | ||
| dnnl.cmake | ||
| eigen.cmake | ||
| extensions.cmake | ||
| find_snpe.cmake | ||
| FindNumPy.cmake | ||
| helper_functions.cmake | ||
| ipp-crypto.cmake | ||
| mimalloc.cmake | ||
| neural_speed.cmake | ||
| onnx_minimal.cmake | ||
| onnx_protobuf.natvis | ||
| onnxruntime_external_deps.cmake | ||
| protobuf_function.cmake | ||
| pybind11.cmake | ||
| pyxir.cmake | ||
| tvm.cmake | ||
| wil.cmake | ||
| xnnpack.cmake | ||