The Ratchet CPU backend is nearly here!
Some remaining work to be done:
- We have a "conflicting" execution model now between CPU and GPU. GPU is applied lazily (i.e we construct a compute graph of all operations and then dispatch to the GPU, for CPU we apply as we build the graph).
- Many operations not yet implemented.
- Matmul optimizations required for performance to be acceptable. Candle did well here with some
wasm128 magic.
The Ratchet CPU backend is nearly here!
Some remaining work to be done:
wasm128magic.