Actions: ModelCloud/GPTQModel
Actions
2,500+ workflow runs
2,500+ workflow runs
weight_only_looper did not support multi-GPU quantization. (#…
Ruff Check
#15983:
Commit 9fd6c8d
pushed
by
Qubitium
weight_only_looper did not support multi-GPU quantization.
Ruff Check
#15982:
Pull request #2915
synchronize
by
ZX-ModelCloud
submodule finalize
Ruff Check
#15981:
Commit d67d8fa
pushed
by
ZX-ModelCloud
weight_only_looper did not support multi-GPU quantization.
Ruff Check
#15980:
Pull request #2915
synchronize
by
ZX-ModelCloud
weight_only_looper did not support multi-GPU quantization.
Ruff Check
#15978:
Pull request #2915
opened
by
ZX-ModelCloud
DeepSeek-V4-Pro experts module can now be correctly dequantized to BF16
Ruff Check
#15975:
Pull request #2914
opened
by
ZX-ModelCloud
tensor.transpose(0, 1).contiguous() when the sha…
Ruff Check
#15973:
Commit 1693760
pushed
by
Qubitium
tensor.transpose(0, 1).contiguous() when the shapes already match
Ruff Check
#15972:
Pull request #2913
synchronize
by
ZX-ModelCloud
tensor.transpose(0, 1).contiguous() when the shapes already match
Ruff Check
#15970:
Pull request #2913
synchronize
by
ZX-ModelCloud
tensor.transpose(0, 1).contiguous() when the shapes already match
Ruff Check
#15968:
Pull request #2913
opened
by
ZX-ModelCloud
tensor.transpose(0, 1).contiguous() when the shapes al…
Ruff Check
#15967:
Commit 4501ed4
pushed
by
ZX-ModelCloud
hy_v3 and ministral3
Ruff Check
#15964:
Pull request #2911
synchronize
by
ZX-ModelCloud
hy_v3 and ministral3
Ruff Check
#15962:
Pull request #2911
synchronize
by
ZX-ModelCloud
hy_v3 and ministral3
Ruff Check
#15960:
Pull request #2911
synchronize
by
ZX-ModelCloud