Daniel Hiltgen
|
cd5c8f6471
Optimize container images for startup (#6547)
|
7 달 전 |
Daniel Hiltgen
|
4a8069f9c4
Quiet down dockers new lint warnings (#6716)
|
7 달 전 |
Daniel Hiltgen
|
6719097649
llm: make load time stall duration configurable via OLLAMA_LOAD_TIMEOUT
|
7 달 전 |
Daniel Hiltgen
|
037a4d103e
Log system memory at info (#6617)
|
8 달 전 |
Sean Khatiri
|
397cae7962
llm: fix typo in comment (#6530)
|
8 달 전 |
Daniel Hiltgen
|
0f92b19bec
Only enable numa on CPUs (#6484)
|
8 달 전 |
Daniel Hiltgen
|
74d45f0102
Refactor linux packaging
|
9 달 전 |
Jeffrey Morgan
|
15c2d8fe14
server: parallelize embeddings in API web handler instead of in subprocess runner (#6220)
|
8 달 전 |
Daniel Hiltgen
|
25906d72d1
llm: prevent loading too large models on windows (#5926)
|
8 달 전 |
Jeffrey Morgan
|
de4fc29773
llm: reserve required number of slots for embeddings (#6219)
|
8 달 전 |
Daniel Hiltgen
|
f457d63400
Implement linux NUMA detection
|
9 달 전 |
Michael Yang
|
b732beba6a
lint
|
9 달 전 |
Michael Yang
|
5c1912769e
Merge pull request #5473 from ollama/mxyng/environ
|
9 달 전 |
royjhan
|
1b44d873e7
Add Metrics to `api\embed` response (#5709)
|
9 달 전 |
Tibor Schmidt
|
f3d7a481b7
feat: add support for min_p (resolve #1142) (#1825)
|
9 달 전 |
Daniel Hiltgen
|
e12fff8810
Enable windows error dialog for subprocess startup
|
9 달 전 |
Michael Yang
|
e2c3f6b3e2
string
|
10 달 전 |
Michael Yang
|
55cd3ddcca
bool
|
10 달 전 |
Michael Yang
|
35b89b2eab
rfc: dynamic environ lookup
|
10 달 전 |
Daniel Hiltgen
|
a3c20e3f18
Refine error reporting for subprocess crash
|
9 달 전 |
Daniel Hiltgen
|
283948c83b
Adjust windows ROCm discovery
|
9 달 전 |
royjhan
|
b9f5e16c80
Introduce `/api/embed` endpoint supporting batch embedding (#5127)
|
9 달 전 |
Jeffrey Morgan
|
ef98803d63
llm: looser checks for minimum memory (#5677)
|
9 달 전 |
Jeffrey Morgan
|
c4cf8ad559
llm: avoid loading model if system memory is too small (#5637)
|
9 달 전 |
Jeffrey Morgan
|
791650ddef
sched: only error when over-allocating system memory (#5626)
|
9 달 전 |
Daniel Hiltgen
|
22c81f62ec
Remove duplicate merge glitch
|
9 달 전 |
Michael Yang
|
9bbddc37a7
Merge pull request #5126 from ollama/mxyng/messages
|
9 달 전 |
Jeffrey Morgan
|
53da2c6965
llm: remove ambiguous comment when putting upper limit on predictions to avoid infinite generation (#5535)
|
9 달 전 |
Michael Yang
|
ac7a842e55
fix model reloading
|
10 달 전 |
Daniel Hiltgen
|
ccd7785859
Merge pull request #5243 from dhiltgen/modelfile_use_mmap
|
10 달 전 |