ollama/llm
Bruce MacDonald 66003e1d05
subprocess improvements (#524)
* subprocess improvements

- increase start-up timeout
- when runner fails to start fail rather than timing out
- try runners in order rather than choosing 1 runner
- embed metal runner in metal dir rather than gpu
- refactor logging and error messages

* Update llama.go

* Update llama.go

* simplify by using glob
2023-09-18 15:16:32 -04:00
..
llama.cpp subprocess improvements (#524) 2023-09-18 15:16:32 -04:00
falcon.go fix: add falcon.go 2023-09-13 14:47:37 -07:00
ggml.go subprocess improvements (#524) 2023-09-18 15:16:32 -04:00
gguf.go subprocess improvements (#524) 2023-09-18 15:16:32 -04:00
llama.go subprocess improvements (#524) 2023-09-18 15:16:32 -04:00
llm.go fix falcon decode 2023-09-12 12:34:53 -07:00
utils.go partial decode ggml bin for more info 2023-08-10 09:23:10 -07:00