Bas Hulsken bbf30d416d

fix: change initialization order of llama-cpp-avx512 to go before avx2 variant (#4837) ...

changed to initialization order of the avx512 version of llama.cpp, now tries before avx2

Signed-off-by: Bas Hulsken <bhulsken@hotmail.com>

2025-02-17 09:32:21 +01:00

..

assets

chore: fix go.mod module (#2635)

2024-06-23 08:24:36 +00:00

concurrency

chore: update jobresult_test.go (#4124)

2024-11-12 08:52:18 +01:00

downloader

chore(downloader): support hf.co and hf:// URIs (#4677)

2025-01-24 08:27:22 +01:00

functions

feat(llama.cpp): Add support to grammar triggers (#4733)

2025-02-02 13:25:03 +01:00

grpc

feat: stream tokens usage (#4415)

2024-12-18 09:48:50 +01:00

langchain

feat(llama.cpp): do not specify backends to autoload and add llama.cpp variants (#2232)

2024-05-04 17:56:12 +02:00

library

rf: centralize base64 image handling (#2595)

2024-06-24 08:34:36 +02:00

model

fix: change initialization order of llama-cpp-avx512 to go before avx2 variant (#4837)

2025-02-17 09:32:21 +01:00

oci

chore: fix go.mod module (#2635)

2024-06-23 08:24:36 +00:00

startup

chore: drop embedded models (#4715)

2025-01-30 00:03:01 +01:00

store

chore: fix go.mod module (#2635)

2024-06-23 08:24:36 +00:00

templates

feat(template): read jinja templates from gguf files (#4332)

2024-12-08 13:50:33 +01:00

utils

feat(tts): Implement naive response_format for tts endpoint (#4035)

2024-11-02 19:13:35 +00:00

xsync

chore: fix go.mod module (#2635)

2024-06-23 08:24:36 +00:00

xsysinfo

feat(default): use number of physical cores as default (#2483)

2024-06-04 15:23:29 +02:00