4 Commits

Author	SHA1	Message	Date
mcm007	bbc07002f7	Update docker and it's configs (#1497) ... * Update ik_llama-cuda.Containerfile - DGGML_NATIVE=ON, as most users are building images locally - Latest llama-swap version * Update ik_llama-cpu.Containerfile - DGGML_NATIVE=ON, as most users are building images locally - Latest llama-swap version * Update README.md - DGGML_NATIVE=ON is now default * Update ik_llama-cuda-swap.config.yaml - Adapt to the latest version * Update ik_llama-cpu-swap.config.yaml - Adapt to the latest version * Update ik_llama-cuda-swap.config.yaml - Add model with aliases * Update ik_llama-cpu-swap.config.yaml - Add model with aliases	2026-03-24 07:52:54 +01:00
mcm007	a6a1da9a28	Fix Issue 1382 (#1424) ... * Use cuda 86 instead of default "default" fails to build * Update docker README.md - Use 86 architecture - Examples for mix of architectures - Where to identify Cuda version - Hint to clean unused images - How to build without llama-swap	2026-03-14 12:27:29 +01:00
mcm007	f80505911d	Improve README.md (#1260)	2026-02-14 09:01:52 +01:00
mcm007	dbcbfdb0ef	Ik llama swap in container step by step guide (#1249) ... * Create README.md * Add container files and llama-swap configs * Update main README.md * Build without GGML_IQK_FA_ALL_QUANTS Otherwise fails with CUDA_DOCKER_ARCH=default * Mention GGML_IQK_FA_ALL_QUANTS usage * First step more explicit	2026-02-07 18:30:19 +02:00