ollama/ml/backend/ggml
Jesse Gross bcd5507f4b
ggml: Support closing backends
In order to iteratively find the best memory allocation, we need to
be able to free backend memory so we can try again.
2025-12-29 06:39:51 -06:00
..
ggml gpt-oss (#11672) 2025-12-29 06:39:48 -06:00
ggml.go ggml: Support closing backends 2025-12-29 06:39:51 -06:00
ggml_test.go gpt-oss (#11672) 2025-12-29 06:39:48 -06:00
mxfp4_test.go gpt-oss (#11672) 2025-12-29 06:39:48 -06:00
quantization.go gpt-oss (#11672) 2025-12-29 06:39:48 -06:00
threads.go ollama debug tensor 2025-03-11 14:49:19 -07:00
threads_debug.go ollama debug tensor 2025-03-11 14:49:19 -07:00