[Hardware][Ascend] Integrate MindIE dense and sparse quantized attention for Wan2.2 T2V (#7561)
Signed-off-by: zqxu <xuzhenqiang3@huawei.com> Co-authored-by: zqxu <xuzhenqiang3@huawei.com>
This commit is contained in:
1 parent
f8197e120f
commit
242c3cddeb
15 files changed
+853
-368
No files matched your search
@@ -941,7 +941,8 @@ class OmniServeCommand(CLISubcommand):
|
||||
"--diffusion-kv-cache-dtype",
|
||||
type=str,
|
||||
default=None,
|
||||
help="Diffusion attention KV cache dtype (e.g. fp8). Separate from vLLM --kv-cache-dtype.",
|
||||
help="Diffusion Q/K/V precision: fp8, mxfp8, mxfp4, or float (NPU). "
|
||||
"Separate from vLLM --kv-cache-dtype. Use --diffusion-attention-config for per-role fallback.",
|
||||
)
|
||||
omni_config_group.add_argument(
|
||||
"--diffusion-kv-cache-skip-steps",
|
||||
|
||||
Reference in new issue
Block a user