"src/turbomind/models/llama/LlamaWeight.cc" did not exist on "ee9627849e8fbeecaf735e1b22fd4e2fa3154ba8"
  1. 20 Nov, 2019 3 commits
  2. 18 Nov, 2019 1 commit
    • Shucai Xiao's avatar
      Improve concat gather (#402) · 0045d0b7
      Shucai Xiao authored
      * improve gather implementation to handle negative input indices
      
      * clang format
      
      * clang format
      
      * improve concat to support neg axis input
      
      * clang format
      
      * fix cppcheck error
      
      * clang format
      
      * code cleanup
      
      * clang format
      
      * fix review comments
      
      * clang format
      0045d0b7
  3. 17 Nov, 2019 1 commit
  4. 15 Nov, 2019 1 commit
    • Paul Fultz II's avatar
      Add option to do offload copying automatically (#403) · 81b0ff5d
      Paul Fultz II authored
      * Add compiler options
      
      * Add copy operators
      
      * Formatting
      
      * Use run_passes in tests
      
      * Formatting
      
      * Use run_pass in schedule test
      
      * Formatting
      
      * Add compile_options to get_passes in target
      
      * Formatting
      
      * Offload copy option
      
      * Formatting
      
      * Copy using pinned memory
      
      * Formatting
      
      * Improve performance of gpu copying
      
      * Formatting
      
      * Dont copy
      
      * Formatting
      
      * Always make an extra copy
      
      * Formatting
      
      * Remove unused write op
      
      * Add missing include
      
      * Remove copy_to_gpu function in python api
      
      * Make offload copy disabled by default on C++
      
      * Formatting
      
      * Fix tidy issues
      
      * Formatting
      
      * Fix namespace
      
      * Fix python tests
      
      * Turn clang format off since its broken
      
      * Fix compile error on gcc 5
      
      * Remove commented code
      81b0ff5d
  5. 14 Nov, 2019 1 commit
    • kahmed10's avatar
      Add Split op (#401) · e814cffb
      kahmed10 authored
      * fix pad calc
      
      * simplify ceil calc and remove extra vars
      
      * workatound for nasnet
      
      * formatting
      
      * add split and tests
      
      * formatting
      
      * fix cppcheck and clang-tidy
      
      * fix clang tidy
      
      * refactor to use vector of instruction_ref, add UNDEBUG to clang tidy
      
      * formatting
      
      * fix comment code
      
      * fix comments and tidy
      
      * formatting
      
      * fix syntax error
      
      * fix tidy
      
      * remove namespace comment
      e814cffb
  6. 06 Nov, 2019 1 commit
  7. 05 Nov, 2019 1 commit
  8. 04 Nov, 2019 2 commits
    • Paul Fultz II's avatar
      Use multi_index for reductions (#400) · 3e0496fb
      Paul Fultz II authored
      * Add functions to do multi-index for local strides as well
      
      * Formatting
      
      * Use same multi-index path for block_reduce
      
      * Formatting
      
      * Use multi-index calc in reduce
      
      * Formatting
      
      * Fix warning
      
      * Fix compiler warning
      
      * Disable some tidy checks
      3e0496fb
    • Paul Fultz II's avatar
      Fix accuraccy issue in resnet50 (#395) · 78c83426
      Paul Fultz II authored
      * Fix bug in eliminate_concat
      
      * Formatting
      
      * Skip context_free operators
      
      * Formatting
      
      * Fix unit test
      
      * Formatting
      78c83426
  9. 30 Oct, 2019 1 commit
    • Paul Fultz II's avatar
      Enable scheduler for 1 stream (#399) · ca17bcd6
      Paul Fultz II authored
      * Enable scheduler for 1 stream
      
      * Formatting
      
      * Improve performance of sorting
      
      * Formatting
      
      * Adjust the weight calculation
      
      * Formatting
      
      * Simplify formula
      
      * Formatting
      
      * Avoid division by zero
      
      * Fix scheduler test
      
      * Check for either 1 or 2
      
      * Check for waits when order may change
      
      * Formatting
      ca17bcd6
  10. 28 Oct, 2019 1 commit
  11. 25 Oct, 2019 2 commits
  12. 24 Oct, 2019 1 commit
  13. 21 Oct, 2019 1 commit
  14. 16 Oct, 2019 3 commits
  15. 15 Oct, 2019 2 commits
  16. 10 Oct, 2019 1 commit
  17. 09 Oct, 2019 1 commit
    • Paul Fultz II's avatar
      Fix bug in bert accuraccy (#385) · a797f890
      Paul Fultz II authored
      * Fix bug in bert accuraccy
      
      * Formatting
      
      * add another test
      
      * Fix add and overflow
      
      * Formatting
      
      * Fix bug in shape_for_each
      
      * Use front instead of iterator
      
      * Use result.front()
      
      * Split add_unary files
      
      * Formatting
      
      * Fix incorrect last index
      
      * Remove comment
      
      * Inline function
      
      * Fix carry check
      
      * Fix metadata errors
      
      * Formatting
      
      * Reflow
      
      * Reflow
      a797f890
  18. 07 Oct, 2019 1 commit
  19. 04 Oct, 2019 1 commit
    • kahmed10's avatar
      Add_clip fusion (#370) · 1398bcc1
      kahmed10 authored
      * initial testing of add_clip fusion
      
      * formatting
      
      * clipped relu fusion
      
      * formatting
      
      * remove some executables, add fusion test
      
      * formatting
      
      * remove clipped_relu code
      
      * fix clang-tidy
      
      * revert changes to cmake files
      
      * remove fusion from weight map
      
      * formatting
      
      * fix syntax error
      
      * formatting
      
      * fix syntax error
      
      * fix syntax error
      
      * formatting
      1398bcc1
  20. 03 Oct, 2019 2 commits
    • Shucai Xiao's avatar
      bug_fix_for_gemm_copy (#378) · 84a3f56e
      Shucai Xiao authored
      * fixed a bug related to removing gemm copy
      
      * clang format
      
      * fix review comments
      
      * clang format
      
      * fix unit test failure
      
      * fix review comments
      
      * clang format
      84a3f56e
    • Paul Fultz II's avatar
      Improve contiguous and concat performance (#368) · 9b55685c
      Paul Fultz II authored
      * Add env to trace nary device functions
      
      * Formatting
      
      * Improve contiguous and concat performance
      
      * Formatting
      
      * Remove unused variable
      
      * Formatting
      
      * Fix gpu tests
      
      * Formatting
      
      * Add more test for transposed concat
      
      * Formatting
      
      * Compute offset and not index
      
      * Compute multi-index once
      
      * Formatting
      
      * Fix transposed inputs
      
      * Formatting
      
      * Use product order for comparisons of hip_array
      
      * Formatting
      
      * Add missing s parameter
      
      * Formatting
      
      * Dont invert permutation
      
      * Fix tidy warnings
      
      * Formatting
      
      * Remove incorrect license
      
      * Use a single integer for stride
      
      * Formatting
      
      * Fix tidy issue
      9b55685c
  21. 02 Oct, 2019 1 commit
    • kahmed10's avatar
      Yapf hook (#369) · 47b05b0c
      kahmed10 authored
      * test hook
      
      * test hook
      
      * test hook
      
      * test hook
      
      * test hook
      
      * test hook
      
      * test hook
      
      * test hook
      
      * test hook
      
      * test hook
      
      * test hook
      
      * test hook
      
      * test hook
      
      * test hook
      
      * test hook
      
      * test hook
      
      * test hook
      
      * test hook
      
      * test hook
      
      * test hook
      
      test hook
      
      test hook
      
      test hook
      
      test hook
      
      test hook
      
      test hook
      
      test hook
      
      test hook
      
      test hook
      
      test hook
      
      test hook
      
      test hook
      
      test hook
      
      test hook
      
      test hook
      
      test hook
      
      test hook
      
      test hook
      
      * # This is a combination of 3 commits.
      # The first commit's message is:
      # This is a combination of 2 commits.
      # The first commit's message is:
      
      test hook
      
      test hook
      
      test hook
      
      test hook
      
      test hook
      
      test hook
      
      test hook
      
      test hook
      
      test hook
      
      test hook
      
      test hook
      
      test hook
      
      test hook
      
      test hook
      
      test hook
      
      test hook
      
      test hook
      
      test hook
      
      test hook
      
      # This is the 2nd commit message:
      
      test hook
      
      # This is the 2nd commit message:
      
      test hook
      
      # This is the 3rd commit message:
      
      test hook
      
      * fix format
      
      * fix format
      
      * ignore doc dir
      
      * fix regex
      
      * fix jenkins error
      
      * exclude another dir
      
      * formatting test_array
      
      * fix version of yapf
      
      * test hook
      
      * formatting
      
      * reinclude dirs
      47b05b0c
  22. 30 Sep, 2019 1 commit
  23. 27 Sep, 2019 1 commit
    • Shucai Xiao's avatar
      Ceil floor operators (#375) · 7d06cdbd
      Shucai Xiao authored
      * add two operators ceil and floor
      
      * clang format
      
      * add unit test for the ceil and floor operators
      
      * remove unintended code
      7d06cdbd
  24. 26 Sep, 2019 1 commit
  25. 25 Sep, 2019 1 commit
    • Shucai Xiao's avatar
      Reduce_min/max operators (#363) · 3962c2ad
      Shucai Xiao authored
      * first version of refactoring reduce operators.
      
      * clang format
      
      * refactor the gpu implemantation of the reduce_mean operator
      
      * clang format
      
      * refactor gpu implementation of the resuce_sum operator
      
      * fix cpp check error
      
      * fix cppcheck error
      
      * fix cppcheck error
      
      * fix review comments
      
      * clang format
      
      * fix a jenkin error
      
      * fixed review comments
      
      * clang format
      
      * fix review comments
      
      * clang format
      
      * fix review comments
      
      * clang format
      
      * add implemenation of reduce_min and reduce_max
      
      * clang format
      
      * add unit test for reduce_min/max operator
      
      * clang format
      
      * add more unit tests
      
      * clang format
      
      * fix review comments
      3962c2ad
  26. 20 Sep, 2019 2 commits
  27. 19 Sep, 2019 1 commit
  28. 18 Sep, 2019 2 commits
    • Paul's avatar
      Add rule to check for incorrect lambda attributes · 7221e973
      Paul authored
      7221e973
    • Shucai Xiao's avatar
      Remove gemm copy and simplify rocblas call (#356) · a0f9b785
      Shucai Xiao authored
      * Remove extra copy in gemm
      
      * combine rocblas gemm call
      
      * clang format
      
      * fix a bug in calling rocblas function
      
      * clang format'
      
      * backup of temporary changes
      
      * clang format
      
      * unify the gemm call to avoid multiple gpu implemantation
      
      * clang format
      
      * remove unnecessary code
      
      * backup temp changes
      
      * clang format
      
      * fix cppcheck error
      
      * code backup
      
      * clang format
      
      * remove unnecessary synchronization function
      
      * clang format
      
      * fix bugs
      
      * clang format
      
      * more optimization related to gemm
      
      * clang format
      
      * code cleanup
      
      * implementation that can achieves better performance
      
      * clang format
      
      * temp changes to try performance
      
      * clang format
      
      * revert to previous commits
      
      * fixed review comments
      
      * clang format
      
      * fix review comments
      a0f9b785
  29. 16 Sep, 2019 2 commits