mirror of
https://github.com/ollama/ollama
synced 2026-04-24 09:14:37 +00:00
9667c2282f
TeaCache: - Timestep embedding similarity caching for diffusion models - Polynomial rescaling with configurable thresholds - Reduces transformer forward passes by ~30-50% FP8 quantization: - Support for FP8 quantized models (8-bit weights with scales) - QuantizedMatmul on Metal, Dequantize on CUDA - Client-side quantization via ollama create --quantize fp8 Other bug fixes: - Fix `/api/show` API for image generation models - Server properly returns model info (architecture, parameters, quantization) - Memory allocation optimizations - CLI improvements for image generation |
||
|---|---|---|
| .. | ||
| examples | ||
| client.go | ||
| client_test.go | ||
| types.go | ||
| types_test.go | ||
| types_typescript_test.go | ||