geoffsee 315ef17605 supports small llama and gemma models ...

Refactor inference

dedicated crates for llama and gemma inferencing, not integrated

2025-08-29 20:00:41 -04:00

..

ARCHITECTURE.md

supports small llama and gemma models

2025-08-29 20:00:41 -04:00

BENCHMARKING.md

Refactor apply_cached_repeat_penalty for optimized caching and reuse, add extensive unit tests, and integrate special handling for gemma-specific models.

2025-08-27 16:15:01 -04:00

OPTIMIZATIONS.md

Refactor apply_cached_repeat_penalty for optimized caching and reuse, add extensive unit tests, and integrate special handling for gemma-specific models.

2025-08-27 16:15:01 -04:00

PERFORMANCE.md

Refactor apply_cached_repeat_penalty for optimized caching and reuse, add extensive unit tests, and integrate special handling for gemma-specific models.

2025-08-27 16:15:01 -04:00

SERVER_CONFIG.md

remove arbitrary keys for standalone config

2025-08-28 13:19:48 -04:00

TESTING.md

Refactor apply_cached_repeat_penalty for optimized caching and reuse, add extensive unit tests, and integrate special handling for gemma-specific models.

2025-08-27 16:15:01 -04:00