Repository Issue Activity (beta)

#217 ResponseCache accounting drift: put() double-counts overwrites, clear() credits zero evictions

#214 run qwen3.5 with integratedGPU

#153 [Feature]: swagger

#213 Windows binary missing?

#182 unknown model architecture: 'qwen35'

#201 docker-compose.yaml

#163 can't load any model on nvidia dgx spark

#210 Compile errors when running `cargo install`

#212 cargo install shimmy 2.3.x is broken for everyone (stale airframe-observe publish + call to never-published airframe API) — fixes + working one-liner inside

#206 Airframe GPU load failed: Model file (12083 MB) exceeds this GPU's storage buffer binding limit (2048 MB).

#205 Airframe GPU backend panics with wgpu Validation Error on TinyLlama Q4_0 GGUF

#169 [Feature]: Add SSD offloading support

#151 [Question]: How shimmy works?

#174 POST failed

#145 [Feature]: Add support for other models such as TTS/SST/image/video/embedding

#137 Better quickstart and demo video/GIF

#131 [Feature]: add support for arm64 in ci/cd

#170 [Bug]: Split GGUF Files for single model not working

#143 [Enhancement]: Add support for uvx

#114 Distribution pipeline failures: MLX support missing from crates.io and Homebrew

#127 Smoke test broken on MLX

#144 [Enhancement]: cargo install should enable mlx by default on apple silicon

#204 [Docs]: Failed to Build from source with Airframe GPU engine

#141 [Question]: Does it support "response.create" in OpenAI API?

#146 Docker image doesn't seem published