We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
There was an error while loading. Please reload this page.
1 parent c00a410 commit 683d72aCopy full SHA for 683d72a
1 file changed
src/mobius/_execution_providers.py
@@ -98,7 +98,7 @@ class EpCapabilities:
98
CUDA / CPU / DML / TRT-RTX where the runtime can handle large
99
pre-allocations.
100
max_buffer_size: Maximum allowed size in bytes for a single model
101
- weight buffer on this EP. ``0`` means no limit. When non-zero,
+ weight buffer on this EP. ``None`` means no limit. When non-zero,
102
large weight tensors (e.g. fused per-layer embedding tables) must
103
be split into chunks that each fit within this bound. WebGPU's
104
W3C spec default ``maxBufferSize`` is 268,435,456 bytes (256 MiB).
0 commit comments