rpenha

Results 6 comments of rpenha

Add React 17 dependencies and update react transition group.

@derrickpelletier or another maintainer, is it possible to accept this PR? It would be nice if we could continue using react-loading-overlay with new react versions. Thanks! 😎

Resolving open generics as singleton caches first request and returns for every other request

Really a annoying bug. No option but to change to another IoC. :(

Error "timed out waiting for llama runner to start: " on larger models.

I'm facing this issue even with small models, like tinyllama. Running `ollama run tinyllama` times out after hard coded 10 minutes timeout. The GPU (RX5700 XT - 8GB with ROCm...

Error "timed out waiting for llama runner to start: " on larger models.

> This should be resolved in the latest release. Please upgrade and if you're still seeing timeouts loading large models on slower systems, share your server log and I'll re-open....

Error "timed out waiting for llama runner to start: " on larger models.

> @rpenha your log is quite short. Let's try another approach. > > ``` > sudo systemctl stop ollama > OLLAMA_DEBUG=1 ollama serve 2>&1 | tee server.log > ``` >...

Error "timed out waiting for llama runner to start: " on larger models.

@dhiltgen, these are my system info: ``` OS: Arch Linux x86_64 Kernel: 6.9.3-zen1-1-zen CPU: Intel Xeon E5-2696 v3 (36) @ 3.800GHz GPU: AMD ATI Radeon RX 5700 XT Memory: 64195MiB...