文件历史

提交图

18 次代码提交

作者 SHA1 备注 提交日期
louistiti 1a11bf755c perf(scripts): improve files download strategy 2025-01-04 10:46:26 +08:00
louistiti 9cb68d5c13 chore: remove unused script 2025-01-04 10:06:22 +08:00
louistiti 025234dbe8 feat(scripts): stop compiling llama.cpp from source and upgrade node-llama-cpp 2025-01-04 09:51:02 +08:00
Ciphreon 067dac6f98 feat(scripts): Update LLM setup script (#547) 2025-01-04 09:18:17 +08:00
louistiti b891a22d2d fix(server): HuggingFace alternative and Llama 3.1 trial 2024-08-05 23:00:36 +08:00
louistiti 0c775ba2e5 feat: use VRAM as LLM unit requirements 2024-07-03 23:41:23 +08:00
louistiti e9f1aadc67 feat(scripts): add Apple Metal developer tools error hint on Apple Silicon for llama.cpp setup 2024-06-01 21:57:20 +08:00
louistiti f1c6db6053 fix(scripts): llama.cpp release tag not failing when null 2024-06-01 21:33:07 +08:00
louistiti 40fd5fac88 fix(scripts): llama.cpp default tag number on LLM setup 2024-06-01 21:04:46 +08:00
louistiti b02d510490 feat(server): always load ASR model from local 2024-05-22 15:22:30 +08:00
louistiti 57923f83ee fix(scripts): always update manifest on LLM setup 2024-04-28 10:10:57 +08:00
louistiti 4ca32b5070 feat(scripts): fallback to mirror in case of error to download LLM 2024-04-22 00:00:46 +08:00
louistiti 2de95c4ef9 feat(server): Gemma support (prototype) 2024-04-16 20:18:18 +08:00
louistiti 49ac3218f7 feat(server): preparing LLM TCP server loading 2024-02-13 16:22:32 +08:00
louistiti 1c0c8080bf feat(scripts): download and compile llama.cpp 2024-02-08 21:05:06 +08:00
louistiti 46f6c09739 scripts(setup-llm): tell when LLM is up-to-date 2024-01-30 00:09:20 +08:00
louistiti 93eb2d22b3 scripts(setup-llm): set up LLM 2024-01-29 23:57:23 +08:00
louistiti c4d2524922 scripts(setup-llm): kick off LLM setup and unify common functions 2024-01-29 00:20:38 +08:00