Diaconu Radu-Mihai
Diaconu Radu-Mihai
Are there any plans to support inference with AMD gpus? As far as I can tell in Candle there is only support for NVIDIA gpus. i am working on safe...
ROCm support
Hello @EricLBuehler Maybe you can add rocm support here by using our rocm wrappers https://github.com/RustNSparks/rocm-rs I could help you
This PR adds sockudo support as broadcasting driver. You can see more details here: https://sockudo.app/ https://github.com/RustNSparks/sockudo
* Included a new "Sockudo" section under "Server Side Installation," detailing: * Sockudo server setup prerequisites. * Installation of the `pusher/pusher-php-server` SDK. * Configuration of the `sockudo` driver in `config/broadcasting.php`...
This Pull Request closes #4184 . It changes the following: - extract small_map as separate utility crate
Dear Soketi Community and Maintainers, Soketi has been a valuable open-source solution for many in the Pusher-compatible WebSocket space. However, as open-source projects evolve, the activity and maintenance landscape can...
- Replace write_vectored with single-buffer writes to avoid fragmentation - Optimize buffer allocation patterns for small/large frames - Improve masking performance with 64-bit operations and better alignment - Add fast-mode...
- Add errorMessage and successMessage props for direct message support - Fix slot validation in computed properties ($slots not available in props) - Add fallback for validation message slots without...