Michael Yang 06b31e2e24 quantize any fp16/fp32 model ...

- FROM /path/to/{safetensors,pytorch}
- FROM /path/to/fp{16,32}.bin
- FROM model:fp{16,32}

2024-05-03 13:18:28 -07:00

..

ext_server

llm: add back check for empty token cache

2024-04-30 17:38:44 -04:00

generate

Do not build AVX runners on ARM64

2024-04-26 23:55:32 -06:00

llama.cpp @ 952d03dbea

update llama.cpp commit to 952d03d

2024-04-30 17:31:20 -04:00

patches

Fix clip log import

2024-04-26 09:43:46 -07:00

filetype.go

quantize any fp16/fp32 model

2024-05-03 13:18:28 -07:00

ggla.go

…

ggml.go

quantize any fp16/fp32 model

2024-05-03 13:18:28 -07:00

gguf.go

fixes for gguf (#3863)

2024-04-23 20:57:20 -07:00

llm_darwin_amd64.go

…

llm_darwin_arm64.go

…

llm_linux.go

…

llm_windows.go

Move nested payloads to installer and zip file on windows

2024-04-23 16:14:47 -07:00

llm.go

quantize any fp16/fp32 model

2024-05-03 13:18:28 -07:00

memory.go

gpu: add 512MiB to darwin minimum, metal doesn't have partial offloading overhead (#4068)

2024-05-01 11:46:03 -04:00

payload.go

Move nested payloads to installer and zip file on windows

2024-04-23 16:14:47 -07:00

server.go

Removing go routine calling .wait from load.

2024-05-01 18:51:10 +00:00

status.go

…