Jeffrey Morgan bbf8f102ee

Revert "llm(llama): pass rope factors (#5924)" (#5963) ...

This reverts commit bb46bbcf5e90e5efab5ff946a6c798131907ba2d.

2024-07-25 18:24:55 -04:00

..

ext_server

Introduce /api/embed endpoint supporting batch embedding (#5127)

2024-07-15 12:14:24 -07:00

generate

Adjust windows ROCm discovery

2024-07-20 15:17:50 -07:00

llama.cpp @ d94c6e0ccb

Update llama.cpp submodule commit to d94c6e0c (#5805)

2024-07-22 12:42:00 -04:00

patches

Revert "llm(llama): pass rope factors (#5924)" (#5963)

2024-07-25 18:24:55 -04:00

filetype.go

…

ggla.go

…

ggml_test.go

…

ggml.go

chatglm graph

2024-07-10 13:43:47 -07:00

gguf.go

add chat and generate tests with mock runner

2024-07-16 09:39:31 -07:00

llm_darwin_amd64.go

…

llm_darwin_arm64.go

…

llm_linux.go

…

llm_windows.go

…

llm.go

fix: quant err message (#5616)

2024-07-11 17:24:29 -07:00

memory_test.go

…

memory.go

…

payload.go

…

server.go

Refine error reporting for subprocess crash

2024-07-22 08:52:16 -07:00

status.go

…