Blake Mizerany 95af97b9f3 server: try github.com/minio/sha256-simd ...

This is an experimental change to see if sha256-simd is faster than the
standard library's sha256 implementation.  It is not yet clear if this
will be a net win, but it is worth trying.

2024-05-31 00:51:20 -07:00

..

ext_server

rm unused infill

2024-05-29 11:26:47 -07:00

generate

speed up tests by only building static lib (#4740)

2024-05-30 21:43:15 -07:00

llama.cpp @ 74f33adf5f

server: try github.com/minio/sha256-simd

2024-05-31 00:51:20 -07:00

patches

Update llama.cpp submodule to 5921b8f0 (#4731)

2024-05-30 16:20:22 -07:00

filetype.go

Add support for IQ1_S, IQ3_S, IQ2_S, IQ4_XS. IQ4_NL (#4322)

2024-05-23 13:21:49 -07:00

ggla.go

simplify safetensors reading

2024-05-21 11:28:22 -07:00

ggml.go

Update llm/ggml.go

2024-05-24 16:10:43 -07:00

gguf.go

simplify safetensors reading

2024-05-21 11:28:22 -07:00

llm_darwin_amd64.go

Switch back to subprocessing for llama.cpp

2024-04-01 16:48:18 -07:00

llm_darwin_arm64.go

Switch back to subprocessing for llama.cpp

2024-04-01 16:48:18 -07:00

llm_linux.go

Switch back to subprocessing for llama.cpp

2024-04-01 16:48:18 -07:00

llm_windows.go

Move nested payloads to installer and zip file on windows

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

llm.go

use int32_t for call to tokenize (#4738)

2024-05-30 21:43:30 -07:00

memory.go

Move envconfig and consolidate env vars (#4608)

2024-05-24 14:57:15 -07:00

payload.go

Move nested payloads to installer and zip file on windows

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

server.go

partial offloading: allow flash attention and disable mmap (#4734)

2024-05-30 16:58:01 -07:00

status.go

Switch back to subprocessing for llama.cpp

2024-04-01 16:48:18 -07:00