Feature(MInference): add triton-based decoding in case flash_attn is … #10
release.yml
on: push
Create Release
4s
Matrix: Build Wheel
Matrix: Publish Python 🐍 distribution 📦 to PyPI
Annotations
86 warnings
Artifacts
Produced during runtime
Name | Size | |
---|---|---|
minference-0.1.4.post3+cu118torch2.0-cp310-cp310-linux_x86_64.whl
Expired
|
3.19 MB |
|
minference-0.1.4.post3+cu118torch2.0-cp311-cp311-linux_x86_64.whl
Expired
|
3.19 MB |
|
minference-0.1.4.post3+cu118torch2.0-cp38-cp38-linux_x86_64.whl
Expired
|
3.19 MB |
|
minference-0.1.4.post3+cu118torch2.0-cp39-cp39-linux_x86_64.whl
Expired
|
3.19 MB |
|
minference-0.1.4.post3+cu118torch2.1-cp310-cp310-linux_x86_64.whl
Expired
|
3.22 MB |
|
minference-0.1.4.post3+cu118torch2.1-cp311-cp311-linux_x86_64.whl
Expired
|
3.22 MB |
|
minference-0.1.4.post3+cu118torch2.1-cp38-cp38-linux_x86_64.whl
Expired
|
3.21 MB |
|
minference-0.1.4.post3+cu118torch2.1-cp39-cp39-linux_x86_64.whl
Expired
|
3.21 MB |
|
minference-0.1.4.post3+cu118torch2.2-cp310-cp310-linux_x86_64.whl
Expired
|
3.37 MB |
|
minference-0.1.4.post3+cu118torch2.2-cp311-cp311-linux_x86_64.whl
Expired
|
3.38 MB |
|
minference-0.1.4.post3+cu118torch2.2-cp38-cp38-linux_x86_64.whl
Expired
|
3.37 MB |
|
minference-0.1.4.post3+cu118torch2.2-cp39-cp39-linux_x86_64.whl
Expired
|
3.37 MB |
|
minference-0.1.4.post3+cu118torch2.3-cp310-cp310-linux_x86_64.whl
Expired
|
3.41 MB |
|
minference-0.1.4.post3+cu118torch2.3-cp311-cp311-linux_x86_64.whl
Expired
|
3.42 MB |
|
minference-0.1.4.post3+cu118torch2.3-cp38-cp38-linux_x86_64.whl
Expired
|
3.41 MB |
|
minference-0.1.4.post3+cu118torch2.3-cp39-cp39-linux_x86_64.whl
Expired
|
3.41 MB |
|
minference-0.1.4.post3+cu122torch2.1-cp310-cp310-linux_x86_64.whl
Expired
|
3.22 MB |
|
minference-0.1.4.post3+cu122torch2.1-cp311-cp311-linux_x86_64.whl
Expired
|
3.22 MB |
|
minference-0.1.4.post3+cu122torch2.1-cp38-cp38-linux_x86_64.whl
Expired
|
3.22 MB |
|
minference-0.1.4.post3+cu122torch2.1-cp39-cp39-linux_x86_64.whl
Expired
|
3.21 MB |
|
minference-0.1.4.post3+cu122torch2.2-cp310-cp310-linux_x86_64.whl
Expired
|
3.37 MB |
|
minference-0.1.4.post3+cu122torch2.2-cp311-cp311-linux_x86_64.whl
Expired
|
3.38 MB |
|
minference-0.1.4.post3+cu122torch2.2-cp38-cp38-linux_x86_64.whl
Expired
|
3.37 MB |
|
minference-0.1.4.post3+cu122torch2.2-cp39-cp39-linux_x86_64.whl
Expired
|
3.37 MB |
|
minference-0.1.4.post3+cu122torch2.3-cp310-cp310-linux_x86_64.whl
Expired
|
3.41 MB |
|
minference-0.1.4.post3+cu122torch2.3-cp311-cp311-linux_x86_64.whl
Expired
|
3.42 MB |
|
minference-0.1.4.post3+cu122torch2.3-cp38-cp38-linux_x86_64.whl
Expired
|
3.41 MB |
|
minference-0.1.4.post3+cu122torch2.3-cp39-cp39-linux_x86_64.whl
Expired
|
3.41 MB |
|