# Permit newer CUDA versions than Clang is aware of
build:cuda_clang --copt="-Wno-unknown-cuda-version"
# Set lld as the linker.
build:cuda_clang --host_linkopt="-fuse-ld=lld"
build:cuda_clang --host_linkopt="-lm"
build:cuda_clang --linkopt="-fuse-ld=lld"
build:cuda_clang --linkopt="-lm"

# Set up compilation CUDA version and paths and use the CUDA Clang toolchain.
build:cuda_clang_official --config=cuda_clang

- gotest.tools/v3: v3.0.3 → v3.0.2
- honnef.co/go/tools: v0.0.1-2019.2.3 → ea95bdf
- k8s.io/gengo/v2: 51d4e06 → 2b36238
- k8s.io/kube-openapi: 70dd376 → f7e401e

### Removed
- bazil.org/fuse: 371fbbd
- cloud.google.com/go/storage: v1.0.0
- dmitri.shuralyov.com/gpu/mtl: 666a987
- github.com/BurntSushi/xgb: [27f1227](https://github.com/BurntSushi/xgb/tree/27f1227)

    *   Added `tf.test.experimental.sync_devices`, which is useful for accurately measuring performance in benchmarks.

*   `tf.experimental.dtensor`:

    *   Added experimental support to ReduceScatter fuse on GPU (NCCL).

### Bug Fixes and Other Changes

*   `tf.SavedModel`: