Oliver Walsh e956d11d70 Use default (auto) value for llama.cpp flash-attn ...

Also fix the uses_nvidia logic which was inverted.

Signed-off-by: Oliver Walsh <owalsh@redhat.com>

2026-01-29 12:21:11 +00:00

..

command

Use default (auto) value for llama.cpp flash-attn

2026-01-29 12:21:11 +00:00

data

Fix quadlet generation for multi-part models

2026-01-02 11:59:55 -05:00

providers

adds support for hosted chat providers

2026-01-24 16:00:59 -06:00

conftest.py

…

test_api_providers.py

adds support for hosted chat providers

2026-01-24 16:00:59 -06:00

test_api_transport.py

refactor to improve command perf time

2026-01-25 02:26:09 -06:00

test_benchmarks_manager.py

adds benchmark metrics persistence

2026-01-24 22:06:46 -06:00

test_chat_provider_base.py

adds support for hosted chat providers

2026-01-24 16:00:59 -06:00

test_cli_arg_normalization.py

small daemon bugfix for docker users and better pull config handling

2025-10-10 09:36:34 -05:00

test_cli_args.py

adds support for hosted chat providers

2026-01-24 16:00:59 -06:00

test_cli.py

Added mapping of https to specific transport

2025-11-07 15:45:34 +01:00

test_common.py

Merge pull request #2309 from ramalama-labs/imp/command-load-time

2026-01-29 03:29:12 -06:00

test_compat.py

Workaround missing NamedTemporaryFile delete_on_close in python 3.10

2025-12-11 17:28:01 +00:00

test_compose.py

…

test_config_documentation.py

adds benchmark metrics persistence

2026-01-24 22:06:46 -06:00

test_config.py

rebased to main

2026-01-25 02:27:24 -06:00

test_engine.py

refactor to improve command perf time

2026-01-25 02:26:09 -06:00

test_file_loader_integration.py

adds support for hosted chat providers

2026-01-24 16:00:59 -06:00

test_file_loader_with_data.py

adds support for hosted chat providers

2026-01-24 16:00:59 -06:00

test_file_loader.py

adds support for hosted chat providers

2026-01-24 16:00:59 -06:00

test_kube.py

Add support for converting to OCI artifacts

2025-12-15 08:16:39 -05:00

test_layered_config.py

…

test_max_tokens.py

Added --max-tokens to llama.cpp inference spec

2025-10-23 14:19:49 +02:00

test_model_store.py

Unit test improvements suggested by sourcery

2025-12-12 18:24:21 +00:00

test_oci.py

convert: run conversion and quantization in runtime containers

2025-10-23 16:16:32 -07:00

test_ollama.py

Fix handling of binary files

2025-12-12 16:33:23 +00:00

test_proxy_support.py

Add SOCKS proxy support

2025-11-19 15:44:36 -05:00

test_quadlet.py

Fix quadlet generation for multi-part models

2026-01-02 11:59:55 -05:00

test_rlcr.py

Add support for converting to OCI artifacts

2025-12-15 08:16:39 -05:00

test_template_conversion.py

removed style conversion system, switched to default jinja and go templates

2025-10-09 14:24:33 -05:00

test_toml_parser.py

whitespace-only changes to be consistent with black 26.1 standards

2026-01-21 13:56:33 -08:00

test_transport_base.py

test fixes

2026-01-25 02:26:11 -06:00

test_transport_factory.py

adds support for hosted chat providers

2026-01-24 16:00:59 -06:00

test_url.py

…