Morph MORPH
SIGN IN SIGN UP
mudler / LocalAI UNCLAIMED

LocalAI is the open-source AI engine. Run any model - LLMs, vision, voice, image, video - on any hardware. No GPU required.

0 0 66 Go

COMMITS

/ core/backend/options.go
master
May 30, 2026
L
feat: prefix-cache-aware routing for distributed mode (#10071)
LocalAI [bot] committed
a44bdb2
May 25, 2026
R
feat(middleware): Model routing, PII filtering, Cloud model proxies (#9802)
Richard Palethorpe committed
6a80e23
May 23, 2026
L
fix(traces): cap backend trace Data to keep admin UI responsive (#9960)
LocalAI [bot] committed
1198d10
May 22, 2026
L
feat(config): default prompt_cache_all to true (#9951)
LocalAI [bot] committed
c500461
May 5, 2026
L
fix(backend): resolve relative draft_model paths against the models dir (#9680)
LocalAI [bot] committed
70cf8ac
April 28, 2026
R
feat(vllm): expose AsyncEngineArgs via generic engine_args YAML map (#9563)
Richard Palethorpe committed
4916f8c
March 31, 2026
E
feat: add node reconciler, allow to schedule to group of nodes, min/max autoscaler (#9186)
Ettore Di Giacinto committed
8862e3c
March 29, 2026
E
feat: add distributed mode (#9124)
Ettore Di Giacinto committed
59108fb
March 21, 2026
E
feat: inferencing default, automatic tool parsing fallback and wire min_p (#9092)
Ettore Di Giacinto committed
031a36c
March 18, 2026
R
feat(ui): Per model backend logs and various fixes (#9028)
Richard Palethorpe committed
35d509d
March 15, 2026
L
fix: Automatically disable mmap for Intel SYCL backends (#9012) (#9015)
LocalAI [bot] committed
c6a5128
March 5, 2026
E
feat: pass-by metadata to predict options (#8795)
Ettore Di Giacinto committed
580517f
January 2, 2026
E
fix(llama.cpp/mmproj): fix loading mmproj in nested sub-dirs different from model path (#7832)
Ettore Di Giacinto committed
5f6c941
December 21, 2025
E
chore(refactor): move logging to common package based on slog (#7668)
Ettore Di Giacinto committed
c37785b
November 16, 2025
E
feat: add support to logitbias and logprobs (#7283)
Ettore Di Giacinto committed
d7f9f3a
October 10, 2025
E
fix(llama.cpp): correctly set grammar triggers (#6432)
Ettore Di Giacinto committed
cd1e112
August 31, 2025
E
feat(flash_attention): set auto for flash_attention in llama.cpp (#6168)
Ettore Di Giacinto committed
739573e
August 14, 2025
E
feat(backends): add system backend, refactor (#6059)
Ettore Di Giacinto committed
089efe0
July 22, 2025
E
feat: refactor build process, drop embedded backends (#5875)
Ettore Di Giacinto committed
98e5291
June 28, 2025
E
feat(llama.cpp): allow to set kv-overrides (#5745)
Ettore Di Giacinto committed
dfadc36
May 22, 2025
E
feat(llama.cpp): add reranking (#5396)
Ettore Di Giacinto committed
3b0cf52
May 3, 2025
E
chore(defaults): enlarge defaults, drop gpu layers which is infered (#5308)
Ettore Di Giacinto committed
b2f9fc8
April 19, 2025
E
chore(autogptq): drop archived backend (#5214)
Ettore Di Giacinto committed
61cc76c
April 1, 2025
E
feat(loader): enhance single active backend by treating as singleton (#5107)
Ettore Di Giacinto committed
2c425e9
March 5, 2025
E
chore(deps): update llama.cpp and sync with upstream changes (#4950)
Ettore Di Giacinto committed
67f7bff
February 18, 2025
B
feat(vllm): Additional vLLM config options (Disable logging, dtype, and Per-Prompt media limits) (#4855)
Brandon Beiler committed
6a6e1a0
February 2, 2025
E
feat(llama.cpp): Add support to grammar triggers (#4733)
Ettore Di Giacinto committed
1d6afbd
January 17, 2025
E
chore(vall-e-x): Drop backend (#4619)
Ettore Di Giacinto committed
7d0ac1e
December 6, 2024
E
feat(llama.cpp): expose cache_type_k and cache_type_v for quant of kv cache (#4329)
Ettore Di Giacinto committed
d4c1746
December 3, 2024
E
feat(backend): add stablediffusion-ggml (#4289)
Ettore Di Giacinto committed
44a5dac
November 8, 2024
E
chore(refactor): drop unnecessary code in loader (#4096)
Ettore Di Giacinto committed
6daef00
November 5, 2024
E
feat(diffusers): allow multiple lora adapters (#4081)
Ettore Di Giacinto committed
947224b
October 23, 2024
E
feat(vllm): expose 'load_format' (#3943)
Ettore Di Giacinto committed
ae1ec4e
October 2, 2024
E
feat: track internally started models by ID (#3693)
Ettore Di Giacinto committed
0965c6c
September 22, 2024
S
feat: auto load into memory on startup (#3627)
Sertaç Özercan committed
ee21b00
July 15, 2024
E
feat(llama.cpp): support embeddings endpoints (#2871)
Ettore Di Giacinto committed
35561ed
June 26, 2024
E
feat(options): add `repeat_last_n` (#2660)
Ettore Di Giacinto committed
a8bfb6f
June 23, 2024
S
chore: fix go.mod module (#2635)
Sertaç Özercan committed
5866fc8
May 13, 2024
E
feat(llama.cpp): add `flash_attention` and `no_kv_offloading` (#2310)
Ettore Di Giacinto committed
e49ea01
April 26, 2024
D
fix: security scanner warning noise: error handlers part 1 (#2141)
Dave committed
2cd4936
April 25, 2024
D
fix: reduce chmod permissions for created files and directories (#2137)
Dave committed
c8dd8e5
April 20, 2024
T
Add tensor_parallel_size setting to vllm setting items (#2085)
Taikono-Himazin committed
03adc1f
April 17, 2024
E
Revert #1963 (#2056)
Ettore Di Giacinto committed
af9e5a2
April 13, 2024
D
refactor: backend/service split, channel-based llm flow (#1963)
Dave committed
eed5706
April 6, 2024
E
fix(llama.cpp): set better defaults for llama.cpp (#1961)
Ettore Di Giacinto committed
8342553
April 3, 2024
E
fix(seed): generate random seed per-request if -1 is set (#1952)
Ettore Di Giacinto committed
ff77d3b
March 13, 2024
E
fix(config): set better defaults for inferencing (#1822)
Ettore Di Giacinto committed
f895d06
March 7, 2024
E
feat(intel): add diffusers/transformers support (#1746)
Ettore Di Giacinto committed
5d10184
March 1, 2024
L
Bump vLLM version + more options when loading models in vLLM (#1782)
Ludovic Leroux committed
9394113
D
refactor: move remaining api packages to core (#1731)
Dave committed
1c31268