"...sglang/srt/layers/triton_attention/decode_attention.py" did not exist on "e1eae1fd15ed8e125ddcd18d0193ae8529c0c309"
  1. 06 May, 2023 1 commit
    • Chris Austen's avatar
      Rocm56 dynbatch (#1737) · 2e128d9d
      Chris Austen authored
      
      
      * Removed split_single_dyn_dim compile flag (#1711)
      * Update C/C++ API for dynamic batch (#1712)
      * Python API update for dynamic batch (#1723)
      * Dynamic batch C++ API example #1728
      * Optimize file space of github runners (#1743)
      Co-authored-by: default avatarCharlie Lin <charlie.lin@amd.com>
      2e128d9d
  2. 06 Apr, 2023 1 commit
    • Charlie Lin's avatar
      Driver dynamic batch update (#1652) · adccec52
      Charlie Lin authored
      Examples..
      
      bin/driver verify /codes/onnx_models/resnet50-v1-7/resnet50-v1-7.onnx --split-single-dyn-dim --batch 3 --dyn-input-dim @data "[{min:1, max:4}, 3, 224, 224]"
      
      bin/driver compile /codes/onnx_models/resnet50-v1-7/resnet50-v1-7.onnx --split-single-dyn-dim --default-dyn-dim "{min:1, max:10}" --output resnet50_batch1-10.mxr
      
      bin/driver perf resnet50_batch1-10.mxr --batch 4
      adccec52
  3. 28 Mar, 2023 1 commit
  4. 16 Feb, 2023 1 commit
  5. 23 Nov, 2022 1 commit
  6. 23 Jun, 2022 1 commit
  7. 17 Aug, 2021 1 commit
  8. 20 Jan, 2021 1 commit
    • turneram's avatar
      Added initial examples (#672) · 7ecc003b
      turneram authored
      * Added initial examples
      
      * Added python example from wiki
      
      * Edited readme
      
      * Added cpp interface files
      
      * Made changes to readmes
      
      * Added jupyter notebook for tf2 ex, added readme for tf1 ex
      
      * Added dockerfile
      
      * Re-structured driver example
      
      * Removed unnecessary files
      
      * Changed include path
      
      * Removed cpp_interface to rewrite
      
      * Added example of parsing, loading, saving with C++ API
      
      * Updated readme
      
      * Small code change, altered docker invocation, formatiing
      
      * Formatting
      
      * Added newline to end of dockerfile
      
      * Formatting
      
      * Formatting
      
      * Added C++ API inference example program
      
      * Formatting
      
      * Added README to cpp inference example
      
      * DeepCode suggested changed
      
      * DeepCode suggested change
      
      * Redesign python inference example
      
      * Address review comments
      
      * Address review comments
      
      * Address review comments
      7ecc003b