Sam
|
1bdab9fdb1
llm: introduce k/v context quantization (vRAM improvements) (#6279)
|
5 months ago |
Jeffrey Morgan
|
55ea963c9e
update default model to llama3.2 (#6959)
|
7 months ago |
Patrick Devine
|
5804cf1723
documentation for stopping a model (#6766)
|
7 months ago |
Jeffrey Morgan
|
83a9b5271a
docs: update examples to use llama3.1 (#6718)
|
7 months ago |
SnoopyTlion
|
741affdfd6
docs: update faq.md for OLLAMA_MODELS env var permissions (#6587)
|
8 months ago |
Michael Yang
|
bb362caf88
update faq
|
10 months ago |
Daniel Hiltgen
|
1a83581a8e
Merge pull request #5895 from dhiltgen/sched_faq
|
9 months ago |
Jeffrey Morgan
|
0e4d653687
upate to `llama3.1` elsewhere in repo (#6032)
|
9 months ago |
Daniel Hiltgen
|
830fdd2715
Better explain multi-gpu behavior
|
9 months ago |
Daniel Hiltgen
|
1f50356e8e
Bump ROCm on windows to 6.1.2
|
9 months ago |
Daniel Hiltgen
|
69c04eecc4
Add windows radeon concurreny note
|
10 months ago |
Daniel Hiltgen
|
aae56abb7c
Document concurrent behavior and settings
|
10 months ago |
Patrick Devine
|
3bade04e10
doc updates for the faq/troubleshooting (#4565)
|
11 months ago |
Patrick Devine
|
f1548ef62d
update the FAQ to be more clear about windows env variables (#4415)
|
11 months ago |
Jeffrey Chen
|
d091fe3c21
Windows automatically recognizes username (#3214)
|
1 year ago |
Daniel Hiltgen
|
20f6c06569
Make maximum pending request configurable
|
1 year ago |
Dr Nic Williams
|
e8aaea030e
Update 'llama2' -> 'llama3' in most places (#4116)
|
1 year ago |
Patrick Devine
|
74d2a9ef9a
add OLLAMA_KEEP_ALIVE env variable to FAQ (#3865)
|
1 year ago |
Patrick Devine
|
1b272d5bcd
change `github.com/jmorganca/ollama` to `github.com/ollama/ollama` (#3347)
|
1 year ago |
Daniel Hiltgen
|
d8fdbfd8da
Add docs for GPU selection and nvidia uvm workaround
|
1 year ago |
Bruce MacDonald
|
a5ba0fcf78
doc: faq gpu compatibility (#3142)
|
1 year ago |
Jeffrey Morgan
|
3a30bf56dc
Update faq.md
|
1 year ago |
Jeffrey Morgan
|
7ed3e94105
Update faq.md
|
1 year ago |
jmorganca
|
2297ad39da
update `faq.md`
|
1 year ago |
Daniel Hiltgen
|
b53229a2ed
Add docs explaining GPU selection env vars
|
1 year ago |
Jeffrey Morgan
|
f0425d3de9
Update faq.md
|
1 year ago |
Jeffrey Morgan
|
df56f1ee5e
Update faq.md
|
1 year ago |
Jeffrey Morgan
|
41aca5c2d0
Update faq.md
|
1 year ago |
Patrick Devine
|
9a7a4b9533
add faqs for memory pre-loading and the keep_alive setting (#2601)
|
1 year ago |
Daniel Hiltgen
|
b338c0635f
Document setting server vars for windows
|
1 year ago |