7 Commits

Author	SHA1	Message	Date
Evan Reichard	682b7d8b4b	feat(llama-swap): add Qwen3 Coder Next 80B model configuration ... Add new model "Qwen3 Coder Next (80B) - Instruct" with 262144 context window and optimized parameters for coding tasks. Uses CUDA unified memory support.	2026-02-03 20:53:47 -05:00
Evan Reichard	7080727dce	chore: update llama-cpp to b7898 and opencode to v1.1.48 ... - Update llama-cpp from b7867 to b7898 - Update opencode from v1.1.12 to v1.1.48 with improved build process: - Replace custom bundle script with official script/build.ts - Add shell completion support - Add version check testing - Simplify node_modules handling - Update llama-swap service config with new llama.cpp options - Clarify opencode agent testing workflow in developer and reviewer configs	2026-02-03 20:33:14 -05:00
Evan Reichard	0dca9802e6	feat(llama-swap): increase context window and add GPU configuration ... - Increase context window from 80k to 202,752 tokens - Add repeat penalty parameter (1.0) - Enable CUDA device for GPU acceleration	2026-01-29 21:18:34 -05:00
Evan Reichard	72ddbb288e	chore: update dependencies and add OpenCode commit command ... - Update llama.cpp from b7789 to b7867 - Update llama-swap from v182 to v186 - Add OpenCode conventional commit command configuration - Add moonshotai Kimi-K2.5 model to llama-swap	2026-01-29 21:01:56 -05:00
Evan Reichard	abcbc3250a	fix: printer	2026-01-23 18:32:10 -05:00
Evan Reichard	58fa210eb5	update llamacpp	2026-01-20 20:20:50 -05:00
Evan Reichard	408151b2ec	chore: various improvements & refactor	2026-01-17 09:28:38 -05:00