QuixiAI releases a C-based embedding inference engine with CPU, CUDA and ROCm support
QuixiAI · x · 2026-07-21
- QuixiAI posts embeddinggemma.c, a fast cross-platform embedding inference engine written in C.
- It runs embeddinggemma-300M-qat-q40-GGUF with a 2k context and focuses on inference only.
- The engine includes optimized kernels for CPU, Metal, CUDA, ROCm, and SYCL.
- It also supports Matryoshka embeddings at 768, 512, 256, and 128 dimensions and exposes a standard HTTP API.
Related event: QuixiAI Open-Sources Cross-Platform C Language Embedding Engine(2 posts)→
More from Research
- Interpretability researcher mathildepapillo joins Goodfire post-PhD, calls interp the key problem — mathildepapillo · 2026-10-27
- Reasoning models can barely control their chain of thought, paper finds — tomekkorbak · 2026-10-27
- New paper: LLM data schedules and learning rate schedules should be co-designed — jasondeanlee · 2026-10-27
- What makes research get adopted: important problems, proper evals, and usability — srchvrs · 2026-10-27
- Bitter lesson part 2: few academic inventions matter, and conference publications aren't the key — srchvrs · 2026-10-27
- First-week PhD student lands ARR Area Chair role, exposing peer-review quirks — anmarasovic · 2026-10-27