diff options
| author | Tim Dettmers <tim.dettmers@gmail.com> | 2022-07-26 19:38:01 -0700 |
|---|---|---|
| committer | Tim Dettmers <tim.dettmers@gmail.com> | 2022-07-26 19:38:01 -0700 |
| commit | 5737f2b027a1e0ec8540a3aa914632d44ad9c62d (patch) | |
| tree | b288c905eaba75dc6b43a8bcebc82720c16e4816 /CHANGELOG.md | |
| parent | 47a73d94c3d3284f6073b0ff189ed5bc9e3a8762 (diff) | |
| parent | dc8c9efdb33130f960adc864916b67d0cb744dbb (diff) | |
Merge branch 'patch_merge' into extract_outliers
Diffstat (limited to 'CHANGELOG.md')
| -rw-r--r-- | CHANGELOG.md | 14 |
1 files changed, 14 insertions, 0 deletions
diff --git a/CHANGELOG.md b/CHANGELOG.md index fa20b15..285984e 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -53,3 +53,17 @@ Bug fixes: Docs: - Added instructions how to solve "\_\_fatbinwrap_" errors. + + +### 0.30.0 + +#### 8-bit Inference Update + +Features: + - Added 8-bit matrix multiplication form cuBLAS, and cuBLASLt as well as multiple GEMM kernels (GEMM, GEMMEx, GEMMLt) + - Added 8-bit Linear layers with 8-bit Params that perform memory efficient inference with an option for 8-bit mixed precision matrix decomposition for inference without performance degradation + - Added quantization methods for "fake" quantization as well as optimized kernels vector-wise quantization and equalization as well as optimized cuBLASLt transformations + - CPU only build now available (Thank you, @mryab) + +Deprecated: + - Pre-compiled release for CUDA 9.2, 10.0, 10.2 no longer available |