- [Deprecation warnings](#deprecation-warnings)
    - [Avoiding permanent beta](#avoiding-permanent-beta)
    - [Expanded CLI support for debugging workloads and nodes](#expanded-cli-support-for-debugging-workloads-and-nodes)
    - [Structured logging](#structured-logging)
    - [EndpointSlices are now enabled by default](#endpointslices-are-now-enabled-by-default)

## Major Features and Improvements

*   Support for Python3.9 has been added.
*   `tf.data`:
    *   `tf.data` service now supports strict round-robin reads, which is useful
        for synchronous training workloads where example sizes vary. With strict
        round robin reads, users can guarantee that consumers get similar-sized
        examples in the same step.

overwritten. x must already be reduced modulo m. // // m must be odd, or Exp will panic. // //go:norace func (out *Nat) Exp(x *Nat, e []byte, m *Modulus) *Nat { if !m.odd { panic("bigmod: modulus for Exp must be odd") } // We use a 4 bit window. For our RSA workload, 4 bit windows are faster // than 2 bit windows, but use an extra 12 nats worth of scratch space. // Using bit sizes that don't divide 8 are more complex to implement, but // are likely to be more efficient if necessary. table := [(1 << 4) - 1]*Nat{...

overwritten. x must already be reduced modulo m. // // m must be odd, or Exp will panic. // //go:norace func (out *Nat) Exp(x *Nat, e []byte, m *Modulus) *Nat { if !m.odd { panic("bigmod: modulus for Exp must be odd") } // We use a 4 bit window. For our RSA workload, 4 bit windows are faster // than 2 bit windows, but use an extra 12 nats worth of scratch space. // Using bit sizes that don't divide 8 are more complex to implement, but // are likely to be more efficient if necessary. table := [(1 << 4) - 1]*Nat{...