v0.6.24

Neo tensor (#20)

* Implement ref count cache.

* `Tensor`'s meta data is also `View`.

* When creating tensor, use ref count cache.

* Fully leverages ref count buffer.

* Do not use temporary cache when loading the model.

* Ref count cache correctly initializes resources.

* Unify cache types.

* Reformat code.

* Bump version to v0.6.25

v0.6.23

Allow loading tensor deltas in LoRA and for embedding.

v0.6.22

Getters for tokenizer.

v0.6.21

Less memory footprint when loading.

v0.6.20

Don't require `Send + Sync` when implementing `BuildFuture`.

v0.6.16

Do not use `async` when building states.

v0.6.14

Update `Reader` interface.

v0.6.13

Require `BackedState` to be serializable.

v0.6.12

Lock `web-rwkv-derive` version.

v0.6.11

Better handling limits.