Daniel Hiltgen
|
f56aa20014
Centralize server config handling
|
1 year ago |
Daniel Hiltgen
|
20f6c06569
Make maximum pending request configurable
|
1 year ago |
Michael Yang
|
b7a87a22b6
Merge pull request #4059 from ollama/mxyng/parser-2
|
1 year ago |
Michael Yang
|
e9ae607ece
Merge pull request #3892 from ollama/mxyng/parser
|
1 year ago |
Michael Yang
|
45b6a12e45
server: target invalid
|
1 year ago |
Michael Yang
|
119589fcb3
rename parser to model/file
|
1 year ago |
Michael Yang
|
9cf0f2e973
use parser.Format instead of templating modelfile
|
1 year ago |
Jeffrey Morgan
|
bb31def011
return code `499` when user cancels request while a model is loading (#3955)
|
1 year ago |
Michael Yang
|
592dae31c8
update copy to use model.Name
|
1 year ago |
Daniel Hiltgen
|
34b9db5afc
Request and model concurrency
|
1 year ago |
Jeffrey Morgan
|
a0b8a32eb4
Terminate subprocess if receiving `SIGINT` or `SIGTERM` signals while model is loading (#3653)
|
1 year ago |
Michael Yang
|
9502e5661f
cgo quantize
|
1 year ago |
Michael Yang
|
e1c9a2a00f
no blob create if already exists
|
1 year ago |
Daniel Hiltgen
|
6589eb8a8c
Revert options as a ref in the server
|
1 year ago |
Daniel Hiltgen
|
58d95cc9bd
Switch back to subprocessing for llama.cpp
|
1 year ago |
Michael Yang
|
91b3e4d282
update memory calcualtions
|
1 year ago |
Michael Yang
|
af8a8a6b59
fix: trim quotes on OLLAMA_ORIGINS
|
1 year ago |
Patrick Devine
|
1b272d5bcd
change `github.com/jmorganca/ollama` to `github.com/ollama/ollama` (#3347)
|
1 year ago |
Blake Mizerany
|
703684a82a
server: replace blob prefix separator from ':' to '-' (#3146)
|
1 year ago |
Patrick Devine
|
47cfe58af5
Default Keep Alive environment variable (#3094)
|
1 year ago |
Daniel Hiltgen
|
4a5c9b8035
Finish unwinding idempotent payload logic
|
1 year ago |
Jeffrey Morgan
|
5b3fad9636
separate out `isLocalIP`
|
1 year ago |
Jeffrey Morgan
|
bfec2c6e10
simplify host checks
|
1 year ago |
Jeffrey Morgan
|
5c143af726
add additional allowed hosts
|
1 year ago |
Jeffrey Morgan
|
fc8c044584
add allowed host middleware and remove `workDir` middleware (#3018)
|
1 year ago |
Daniel Hiltgen
|
6c5ccb11f9
Revamp ROCm support
|
1 year ago |
Jeffrey Morgan
|
3b4bab3dc5
Fix embeddings load model behavior (#2848)
|
1 year ago |
Michael Yang
|
0e19476b56
prepend image tags (#2789)
|
1 year ago |
Jeffrey Morgan
|
287ba11500
better error message when calling `/api/generate` or `/api/chat` with embedding models
|
1 year ago |
Jeffrey Morgan
|
63861f58cc
Support for `bert` and `nomic-bert` embedding models
|
1 year ago |