Connecting fp16xq4 gemm kernels (optimized for A100) to MatMulNBits<fp16> operator #31297
lint.yml
on: pull_request
Optional Lint
32s
Python format
3m 39s
Lint C++
24m 13s
Lint JavaScript
24s
Annotations
1 error and 16 warnings
Lint C++
reviewdog: Too many results (annotations) in diff.
You may miss some annotations due to GitHub limitation for annotation created by logging command.
Please check GitHub Actions log console to see all results.
Limitation:
- 10 warning annotations and 10 error annotations per step
- 50 annotations per job (sum of annotations from all the steps)
- 50 annotations per run (separate from the job annotations, these annotations aren't created by users)
Source: https://github.com/orgs/community/discussions/26680#discussioncomment-3252835
|
Python format
Node.js 16 actions are deprecated. Please update the following actions to use Node.js 20: actions-rs/toolchain@v1. For more information see: https://github.blog/changelog/2023-09-22-github-actions-transitioning-from-node-16-to-node-20/.
|
Python format
The following actions uses node12 which is deprecated and will be forced to run on node16: actions-rs/toolchain@v1. For more info: https://github.blog/changelog/2023-06-13-github-actions-all-actions-will-run-on-node16-instead-of-node12-by-default/
|
Python format
The `set-output` command is deprecated and will be disabled soon. Please upgrade to using Environment Files. For more information see: https://github.blog/changelog/2022-10-11-github-actions-deprecating-save-state-and-set-output-commands/
|
Python format
The `set-output` command is deprecated and will be disabled soon. Please upgrade to using Environment Files. For more information see: https://github.blog/changelog/2022-10-11-github-actions-deprecating-save-state-and-set-output-commands/
|
Python format
The `set-output` command is deprecated and will be disabled soon. Please upgrade to using Environment Files. For more information see: https://github.blog/changelog/2022-10-11-github-actions-deprecating-save-state-and-set-output-commands/
|
Python format
The `set-output` command is deprecated and will be disabled soon. Please upgrade to using Environment Files. For more information see: https://github.blog/changelog/2022-10-11-github-actions-deprecating-save-state-and-set-output-commands/
|
Lint C++:
onnxruntime/contrib_ops/cuda/quantization/matmul_nbits.cc#L36
[cpplint] reported by reviewdog 🐶
Using deprecated casting style. Use static_cast<int>(...) instead [readability/casting] [4]
Raw Output:
onnxruntime/contrib_ops/cuda/quantization/matmul_nbits.cc:36: Using deprecated casting style. Use static_cast<int>(...) instead [readability/casting] [4]
|
Lint C++:
onnxruntime/contrib_ops/cuda/quantization/matmul_nbits.cu#L398
[cpplint] reported by reviewdog 🐶
Lines should be <= 120 characters long [whitespace/line_length] [2]
Raw Output:
onnxruntime/contrib_ops/cuda/quantization/matmul_nbits.cu:398: Lines should be <= 120 characters long [whitespace/line_length] [2]
|
Lint C++:
onnxruntime/contrib_ops/cuda/quantization/matmul_nbits.cu#L422
[cpplint] reported by reviewdog 🐶
Lines should be <= 120 characters long [whitespace/line_length] [2]
Raw Output:
onnxruntime/contrib_ops/cuda/quantization/matmul_nbits.cu:422: Lines should be <= 120 characters long [whitespace/line_length] [2]
|
Lint C++:
onnxruntime/contrib_ops/cuda/quantization/matmul_nbits.cu#L469
[cpplint] reported by reviewdog 🐶
Missing space before { [whitespace/braces] [5]
Raw Output:
onnxruntime/contrib_ops/cuda/quantization/matmul_nbits.cu:469: Missing space before { [whitespace/braces] [5]
|
Lint C++:
onnxruntime/contrib_ops/cuda/quantization/matmul_nbits.cu#L535
[cpplint] reported by reviewdog 🐶
{ should almost always be at the end of the previous line [whitespace/braces] [4]
Raw Output:
onnxruntime/contrib_ops/cuda/quantization/matmul_nbits.cu:535: { should almost always be at the end of the previous line [whitespace/braces] [4]
|
Lint C++:
onnxruntime/contrib_ops/cuda/quantization/matmul_nbits.cu#L540
[cpplint] reported by reviewdog 🐶
Lines should be <= 120 characters long [whitespace/line_length] [2]
Raw Output:
onnxruntime/contrib_ops/cuda/quantization/matmul_nbits.cu:540: Lines should be <= 120 characters long [whitespace/line_length] [2]
|
Lint C++:
onnxruntime/contrib_ops/cuda/quantization/matmul_nbits.cu#L542
[cpplint] reported by reviewdog 🐶
Lines should be <= 120 characters long [whitespace/line_length] [2]
Raw Output:
onnxruntime/contrib_ops/cuda/quantization/matmul_nbits.cu:542: Lines should be <= 120 characters long [whitespace/line_length] [2]
|
Lint C++:
onnxruntime/contrib_ops/cuda/quantization/matmul_nbits.cu#L546
[cpplint] reported by reviewdog 🐶
Lines should be <= 120 characters long [whitespace/line_length] [2]
Raw Output:
onnxruntime/contrib_ops/cuda/quantization/matmul_nbits.cu:546: Lines should be <= 120 characters long [whitespace/line_length] [2]
|
Lint C++:
onnxruntime/contrib_ops/cuda/quantization/matmul_nbits.cu#L558
[cpplint] reported by reviewdog 🐶
Lines should be <= 120 characters long [whitespace/line_length] [2]
Raw Output:
onnxruntime/contrib_ops/cuda/quantization/matmul_nbits.cu:558: Lines should be <= 120 characters long [whitespace/line_length] [2]
|
Lint C++:
onnxruntime/contrib_ops/cuda/quantization/matmul_nbits.cu#L560
[cpplint] reported by reviewdog 🐶
Lines should be <= 120 characters long [whitespace/line_length] [2]
Raw Output:
onnxruntime/contrib_ops/cuda/quantization/matmul_nbits.cu:560: Lines should be <= 120 characters long [whitespace/line_length] [2]
|