tabbyAPI-ollama/docs
kingbri 113643c0df Main: Enable cudaMallocAsync backend by default
Works on cuda 12.4 and up. If CUDA doesn't exist, then don't enable
the backend. This is an env var that needs to be set, so it's not really
possible to set it via config.yml.

This used to be experimental, but it's probably fine to keep it enabled
since it only provides a benefit.

Signed-off-by: kingbri <8082010+kingbri1@users.noreply.github.com>
2025-07-27 22:31:38 -04:00
..
01.-Getting-Started.md Docs: Update getting started with downloading from private repos 2025-03-19 12:02:48 -04:00
02.-Server-options.md Main: Enable cudaMallocAsync backend by default 2025-07-27 22:31:38 -04:00
03.-Usage.md Docs: Edit inline loading for breaking changes 2025-07-24 18:11:42 -04:00
04.-Chat-Completions.md API: Add chat_template_kwargs alias for template_vars 2025-05-12 15:48:39 -04:00
05.-FAQ.md Tree: Migrate docs into repository 2025-02-17 23:39:35 -05:00
06.-Sharing.md Tree: Migrate docs into repository 2025-02-17 23:39:35 -05:00
07.-AI-Horde.md Tree: Migrate docs into repository 2025-02-17 23:39:35 -05:00
08.-Sampling.md Tree: Migrate docs into repository 2025-02-17 23:39:35 -05:00
09.-Community-Projects.md Tree: Migrate docs into repository 2025-02-17 23:39:35 -05:00
10.-Tool-Calling.md Docs: Update tool calling 2025-07-05 21:43:04 -04:00
Home.md Tree: Migrate docs into repository 2025-02-17 23:39:35 -05:00