59274d50 · [xla:gpu] Remove AddressComputationFusion emitter · 3月 31, 2024

b727f69a · [xla:gpu][NFC] No need for custom HloModuleConfigs in address_computation_fusion_test · 3月 31, 2024

d566bc7c · [xla:gpu] No need for dynamic/static mode in AddressComputationFusionRewriter · 3月 31, 2024

a30a1322 · Remove XlaOutlineEntryFunctions pass · 3月 29, 2024

28561f93 · Allow MaybeSavedModelDirectory to read via custom env. · 3月 29, 2024

f71f7dac · [xla:gpu][NFC] Simplify `collect_slice_info` · 3月 29, 2024

6e074ff7 · Mhlo to Hlo converters for dynamic_reshape and dynamic_broadcast_in_dim · 3月 29, 2024

30fd697f · [tsl] Mark `tsl::NullTerminatedMessage()` with `ABSL_DEPRECATE_AND_INLINE` · 3月 29, 2024

549cbc02 · [tsl] Implement `tsl::NullTerminatedMessage()` in terms of `absl::StatusMessageAsCStr()` · 3月 29, 2024

1aed65e6 · Split hybrid quantized dot-like StableHLO ops into TFLite dequantize and float op · 3月 29, 2024

4d0d9d61 · Add double buffer removal pass · 3月 28, 2024

0cffb51f · Try to make everything from `tensorflow/third_party` writable via Copybara · 3月 28, 2024

c9fc3112 · Use TpuTilingAssignment for SparseCore inside TpuLayoutAssignment · 3月 28, 2024

096af095 · PR #10759: [XLA:CPU][oneDNN] Enable matrix-vector and vector-vector product · 3月 28, 2024

5df69239 · Add support for binary ops in RTVar optimization · 3月 28, 2024

5c079e7b · #sdy save HloInputOutputAliasConfig and HloBufferDonorConfig in SDY XLA pipeline · 3月 28, 2024

bf105c94 · [JAX] Automatically share PGO data for GPU latency-hiding scheduler. · 3月 28, 2024

9c9562a1 · Add a xla flag `--xla_force_execution_mode` to control execution mode on the CPU backend. · 3月 27, 2024

26aed928 · Fix macos oss build. · 3月 27, 2024

24b12576 · PR #64619: shlo_ref: Disable legacy code build · 3月 27, 2024