Qeravio
Canonical AI event

Hash-cache now only stores weights in RPC protocol.

The update restricts hash caching to weights, preventing unnecessary disk use from activations.

15 Sept 20261 verified claims1 sources2 observations
What happened

The official source reports this update: b10985: rpc : hash-cache only weights. rpc : hash-cache only weights ( #28789 ) rpc : hash-cache only weights ggml_backend_rpc_buffer_set_tensor and ggml_backend_rpc_set_tensor_async hashed every transfer above HASH_THRESHOLD and let rpc-server -c serve it from its file cache. The cache is meant for weights, but the activations ggml_backend_sched copies between backends took the same path: with a two-node split of Qwen3.8-Flash-Next every prefill ubatch above 10 MB was hashed, written to the worker's cache directory (1.4 TB after a day) and later served from there. Use the hash path only for tensors in buffers marked GGML_BACKEND_BUFFER_USAGE_WEIGHTS.

Why it matters

This official update documents a development concerning b10985: rpc : hash-cache only weights. Its practical significance depends on the scope and evidence stated by the source.

What to watch next

Read the official source update and verify its stated scope, evidence and timing before acting on it.

Connected knowledge

Entities affected by this event

Continue this topic
Evidence trail

Sources behind the event