d30aa270 · Expose MR for qd8-f32-qc4w. · Jun 06, 2024

2f56f8e2 · HVX depend on standard microkernel dependencies · Jun 04, 2024

4cdcf425 · Refactor more unary operator benchmarks · Jun 04, 2024

369c849a · Fix error in the packed weights buffer size computation. · Jun 04, 2024

de854973 · Clean up several of the older and currently unused `f32-vtanh` microkernels. · Jun 04, 2024

0d61e0f1 · Rewrite the `f32` `tanh` kernels using the new `SIMD` intrinsics. · Jun 04, 2024

7d5b8a5c · - Adds a new type of `xnn_profile_info` to return node_ids associated with the... · May 29, 2024

870951e7 · SSE41 qs8 rdsum accumulating microkernels · May 28, 2024

477ba721 · Fixes XNNPACK profiling information logged from the xnnpack_delegate.... · May 28, 2024

889dc730 · Add a build identifier to XNNPack derived from the microkernel source files. · May 28, 2024

752e6a37 · Update the `rules_android_ndk` version. · May 28, 2024

bb4eba73 · Fixes ReferenceError of concurrency not being defined. · May 28, 2024

5cbfa963 · Avoid benchmark link errors in Bazel for platforms that don't have... · May 28, 2024

f69ce604 · Remove bench_microkernels build variant (we can just use test_microkernels),... · May 27, 2024

f239b176 · F32-RMINMAXSUM - add reduction sum to f32-rminmax · May 27, 2024

2b977e36 · Remove XNN_TEST_MODE, it appears to be unnecessary, and we should test the... · May 27, 2024

b7dde43e · QS8-RSUM AVX2 use vpmaddubsw · May 27, 2024

9d5e952a · Add a new `x8-packq` microkernel that packs and per-row dynamically quantizes `fp32` to `qp8`. · May 27, 2024

f5e33fb5 · Extend the `convert` operator for the new `qp8` packed per-row dynamic quantization. · May 27, 2024

dc13720d · Add a `xnn_datatype_qpint8` datatype for packed per-row dynamically quantized... · May 27, 2024