huggingface/text-generation-inference Issues
Unknown variant Qwen2
UpdatedError with sharded Mixtral
Updated 4template_error in /chat/completions
Closed 2API_KEY argument
Updated 2[RFC]Add Auto-Round Support
Updated 8`top_p` messes up `top_logprobs`
Updated 2protobuf version not compatible
Updated 1Sparse Marlin
Closed 3Long install report
Updated 1Tree-attention for medusa
Updated 2Fp8 support KV-Cache
Updated