Repository Issue Activity (beta feature)

#

#

#3448 Gemma 4 Model download issues

#

#

#

#3294 [RFC] Candelabra: JAX-style tracing and compilation for Candle

#

#

#

#

#3002 Is there a roadmap or intention to support CUDA Graph?

#

#3389 conv1d with large groups (depthwise) is extremely slow on CUDA — O(groups) kernel launches

#

#

#

#3473 missing <think> and </think> tokens on qwen models

#

#

#

#

#

#

#