Commits · dd41a2235ea1d8180318471198fdf1f0d654a9af · OpenDAS / AutoAWQ

"Python/NLP/Bert/run_onnx_squad.py" did not exist on "b8fc3c491c990a648b238e41f944c114249e71cc"

11 Sep, 2023 7 commits
- Update MPTBlock, fuse with MPTModel · dd41a223
  Casper Hansen authored Sep 11, 2023
  
  dd41a223
- Fix attention, support alibi · 7631add1
  Casper Hansen authored Sep 11, 2023
  
  7631add1
- Create MPTModel class · 90f54dbb
  Casper Hansen authored Sep 11, 2023
  
  90f54dbb
- Initialize with device · e80663bb
  Casper Hansen authored Sep 11, 2023
  
  e80663bb
- Remove fusing attention, only blocks · ac3e86df
  Casper Hansen authored Sep 11, 2023
  
  ac3e86df
- Fuse MPT block · 950851b3
  Casper Hansen authored Sep 11, 2023
  
  950851b3
- Switch to torch SDPA · d7badefc
  Casper Hansen authored Sep 11, 2023
  
  d7badefc
09 Sep, 2023 7 commits
- Falcon fused layers · 54f02854
  Casper Hansen authored Sep 09, 2023
  
  54f02854
- Fix alibi, rotary arg, neox, arg · 73c5e2bf
  Casper Hansen authored Sep 09, 2023
  
  73c5e2bf
- Fuse MPT · f3695d60
  Casper Hansen authored Sep 09, 2023
  
  f3695d60
- Update module name · 5bd6fbc7
  Casper Hansen authored Sep 09, 2023
  
  5bd6fbc7
- Implement ALiBi. · adc5304b
  Casper Hansen authored Sep 09, 2023
  
  adc5304b
- Remove warnings about GEMM · c58ec73b
  Casper Hansen authored Sep 09, 2023
  
  c58ec73b
- Create torch SDPA implementation · ebbbc3a5
  Casper Hansen authored Sep 09, 2023
  
  ebbbc3a5
08 Sep, 2023 10 commits
- GEMM + GEMV compatibility · 890b6aa7
  Casper Hansen authored Sep 08, 2023
  
  890b6aa7
- Use apply_rotary_emb · 64e6b3e1
  Casper Hansen authored Sep 08, 2023
  
  64e6b3e1
- Update kernel, remove unused code · a11c313a
  Casper Hansen authored Sep 08, 2023
  
  a11c313a
- Attention works · fbfa9d82
  Casper Hansen authored Sep 08, 2023
  
  fbfa9d82
- Fix MLP module · 75710806
  Casper Hansen authored Sep 08, 2023
  
  75710806
- Fix variables and no contiguous memory for GEMV · e197a733
  Casper Hansen authored Sep 08, 2023
  
  e197a733
- Fix variables · 6534f5e6
  Casper Hansen authored Sep 08, 2023
  
  6534f5e6
- Implement GEMM/GEMV in quantize function and fused modules · 5db43a7f
  Casper Hansen authored Sep 08, 2023
  
  5db43a7f
- Add deprecation warning · 9b2946b6
  Casper Hansen authored Sep 08, 2023
  
  9b2946b6
- Refactor modules, create separate GEMM and GEMV · fe314160
  Casper Hansen authored Sep 08, 2023
  
  fe314160
07 Sep, 2023 1 commit
- Support Falcon 180B · 475481b4
  Casper authored Sep 07, 2023
  
  475481b4
06 Sep, 2023 8 commits
- Bump version · a0fb91d9
  Casper authored Sep 06, 2023
  
  a0fb91d9
- Remove simple dispatch · 562c0d52
  Casper authored Sep 06, 2023
  
  562c0d52
- Multi-GPU support for quantized models · f8273a0c
  Casper Hansen authored Sep 06, 2023
  
  f8273a0c
- Get correct devices · 7cf0d987
  Casper Hansen authored Sep 06, 2023
  
  7cf0d987
- Correct input sizes · ab7d68e7
  Casper Hansen authored Sep 06, 2023
  
  ab7d68e7
- Switch to model.generate() · a4626828
  Casper Hansen authored Sep 06, 2023
  
  a4626828
- Update shapes for cuda kernel · e71181bd
  Casper Hansen authored Sep 06, 2023
  
  e71181bd
- Use hf_rotary per default · b7290868
  Casper Hansen authored Sep 06, 2023
  
  b7290868
05 Sep, 2023 7 commits
- Remove CustomQuantAttention class · 42655843
  Casper Hansen authored Sep 05, 2023
  
  42655843
- Revert "Update neox kernel" · bbe1d46a
  Casper Hansen authored Sep 05, 2023
```
This reverts commit 4fe9974a.
```
  bbe1d46a
- Update neox kernel · 4fe9974a
  Casper Hansen authored Sep 05, 2023
  
  4fe9974a
- Attempt new module · 8bb8fe20
  Casper Hansen authored Sep 05, 2023
  
  8bb8fe20
- Fix the metrics with batch size · 0f699cf9
  Casper Hansen authored Sep 05, 2023
  
  0f699cf9
- Implement batch size · 883e47d5
  Casper Hansen authored Sep 05, 2023
  
  883e47d5
- Revert to n_context arg · 4f42f509
  Casper Hansen authored Sep 05, 2023
  
  4f42f509