vllm/attention/ops/flashmla.py · ac201a0eaf2af032779db3e7ac96f857cbaa5b7a · OpenDAS / vllm_cscc

"tests/models/quantization/test_gptq_marlin.py" did not exist on "aa4502e7f3d9f53f093bb9b91607617a2223156b"

[Feature] Support Decode Context Parallel (DCP) for MLA (#23734) · ac201a0e

yzds authored Sep 06, 2025


Signed-off-by: hongchao <hongchao@msh.team>
Signed-off-by: youkaichao <youkaichao@gmail.com>
Co-authored-by: hongchao <hongchao@msh.team>
Co-authored-by: youkaichao <youkaichao@gmail.com>

ac201a0e

flashmla.py 4.21 KB

Replace flashmla.py