Daniel Hiltgen db2a9ad1fe Explicitly disable AVX2 on GPU builds ...

Even though we weren't setting it to on, somewhere in the cmake config
it was getting toggled on.  By explicitly setting it to off, we get `/arch:AVX`
as intended.

2024-02-15 14:50:11 -08:00

..

ext_server

set shutting_down to false once shutdown is complete (#2484)

2024-02-13 17:48:41 -08:00

generate

Explicitly disable AVX2 on GPU builds

2024-02-15 14:50:11 -08:00

llama.cpp @ 6c00a06692

Revert "Revert "bump submodule to 6c00a06 (#2479)"" (#2485)

2024-02-13 18:18:41 -08:00

patches

patch: always add token to cache_tokens (#2459)

2024-02-12 08:10:16 -08:00

dyn_ext_server.c

Switch to local dlopen symbols

2024-01-19 11:37:02 -08:00

dyn_ext_server.go

Shutdown faster

2024-02-08 22:22:50 -08:00

dyn_ext_server.h

Always dynamically load the llm server library

2024-01-11 08:42:47 -08:00

ggml.go

add max context length check

2024-01-12 14:54:07 -08:00

gguf.go

refactor tensor read

2024-01-24 10:48:31 -08:00

llama.go

use llm.ImageData

2024-01-31 19:13:48 -08:00

llm.go

Ensure the libraries are present

2024-02-07 17:27:49 -08:00

payload_common.go

Detect AMD GPU info via sysfs and block old cards

2024-02-12 08:19:41 -08:00

payload_darwin_amd64.go

Add multiple CPU variants for Intel Mac

2024-01-17 15:08:54 -08:00

payload_darwin_arm64.go

Add multiple CPU variants for Intel Mac

2024-01-17 15:08:54 -08:00

payload_linux.go

Add multiple CPU variants for Intel Mac

2024-01-17 15:08:54 -08:00

payload_test.go

Fix up the CPU fallback selection

2024-01-11 15:27:06 -08:00

payload_windows.go

Add multiple CPU variants for Intel Mac

2024-01-17 15:08:54 -08:00

utils.go

partial decode ggml bin for more info

2023-08-10 09:23:10 -07:00