Repository Issue Activity (beta)

#10577 failed to download image tar: failed to download layer 0: unexpected EOF

#11483 WarmEstimateCache fetches > 1 GB every start

#11674 sglang backend: enable_thinking=false is dropped, and reasoning_content stays empty for <think>-prefilled templates

#11673 Mac dmg launcher launches nothing

#11566 Remote workers in Distributed Nodes, do not update Context/Token size limit for LLMs.

#11623 whisper backend run.sh forwards LocalAI's positional listen address, but main.go only parses -addr flag — backend always binds :50051

#11635 Tool call arguments are empty on /responses but correct on /chat/completions (same model, same config)

#11626 audio-cpp using a fish-audio doesn't work with referance audio/text

#11624 metal-whisper: ggml_metal_library_init fails to compile embedded Metal shader library on macOS 26.5.2 (Apple M4 Pro) — flash-attn kernel's threadgroup half4x4 array rejected

#11609 TTS Voice Design WebUI

#11621 Vision/multimodal silently dropped with use_tokenizer_template on the python backends (sglang, vllm): images reach the engine but the prompt carries no media placeholder

#11617 Voice Library Improvements

#11604 API to list TTS voices

#11562 voice-detect and face-detect backends SIGSEGV on ROCm (gfx1100) — null pointer in purego.RegisterFunc call

#11593 cuda13-llama-cpp backend crashes loading gemma4 GGUF: "wrong number of tensors; expected 2131, got 720"

#3216 Automatically sync model folder

#11579 Fish Speech backend using ROCM doesn't work

#9534 RFC: Optional server-side context-compression middleware for /v1/chat/completions

#11577 ROCM audio-cpp image

#11564 liquid-audio backend: AudioTransformStream RPC raises NotImplementedError (realtime streaming never works, on any hardware)

#11563 rocm-fish-speech backend ships a CUDA build of PyTorch, never uses the GPU on AMD/ROCm

#10885 Jobs monitor - Add running and queued jobs in traces view.

#9432 feat: persist Chat History server-side

#11534 Shasum error installing audio-cpp-sortformer-diarization

#8934 Intel GPU is not utilized by intel-qwen-asr