You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
In the three implementation files of fp8 sparse gemm vllm/csrc/sparse/cutlass/sparse_scaled_mm__xxx.
Can you abstract the implementation formula of cutlass_scaled_sparse_mm_sm90?
In addition, I understand that bt_nzs bt_meta is the data after gemm weight sparse (from sparse_compressor_xxx), what are the arrangements of the three tensors bt_nzs, a and c respectively (in ColumnMajor RowMajor)?
Before submitting a new issue...
Make sure you already searched for relevant issues, and asked the chatbot living at the bottom right corner of the documentation page, which can answer lots of frequently asked questions.
The text was updated successfully, but these errors were encountered:
Your current environment
How would you like to use vllm
In the three implementation files of fp8 sparse gemm vllm/csrc/sparse/cutlass/sparse_scaled_mm__xxx.
Before submitting a new issue...
The text was updated successfully, but these errors were encountered: