1. 01 7月, 2021 1 次提交
  2. 30 6月, 2021 3 次提交
    • J
      Added matmul_v2 BF16/FP32 FWD kernel (#33750) · 24783c84
      jakpiase 提交于
      * added matmul_v2 bf16/fp32 FWD kernel
      
      added matmul_v2 bf16/fp32 FWD kernel
      
      * added formatting
      
      * removed some tests due to timeout in CI
      
      * refactored tests
      
      * merged tests classes into one file
      
      * minor change
      
      * removed test guard for CUDA
      
      * remove skipIf
      
      * changes after review
      
      * formated one file
      
      * minor change
      
      * added skipping UT in CUDA place
      24783c84
    • A
      [Dy2Stat] Refine PartialProgramLayer logic (#33796) · 97f86d84
      Aurelius84 提交于
      * refine temp_scope_vec logic
      
      * polish partial_program
      
      * fix fake var
      
      * add stop_gradient in spec
      
      * fix fake_var
      
      * fix unittest
      97f86d84
    • H
      [NPU] support set_device (#33815) · 8225a6a1
      houj04 提交于
      * support set_device for NPU.
      
      * minor update doc and add more unit test.
      8225a6a1
  3. 29 6月, 2021 6 次提交
  4. 28 6月, 2021 15 次提交
  5. 25 6月, 2021 4 次提交
  6. 24 6月, 2021 9 次提交
  7. 23 6月, 2021 2 次提交
    • J
      Added split op bf16/fp32 oneDNN kernel (#33584) · 68106509
      jakpiase 提交于
      * base changes for split op
      
      * 90% of split functionality added
      
      * full fp32 functionality
      
      * added bf16 test
      
      * added submemory caching
      
      * added bf test to static mode whitelist
      
      * minor change
      
      * enabled split op for inference
      
      * minor fix
      
      * minor fix
      68106509
    • K
      elastic unitest (#33728) · 9b58cbf1
      kuizhiqing 提交于
      * elastic unitest
      
      * rename demo
      9b58cbf1