 Ryo Machida
|
798b107f19
Fixed the API endpoint /api/tags when the model list is empty. (#4424)
|
il y a 1 an |
 Patrick Devine
|
7ca71a6b0f
don't abort when an invalid model name is used in /save (#4416)
|
il y a 1 an |
|
Patrick Devine
|
6845988807
Ollama `ps` command for showing currently loaded models (#4327)
|
il y a 1 an |
 Jeffrey Morgan
|
6602e793c0
Use `--quantize` flag and `quantize` api parameter (#4321)
|
il y a 1 an |
 Michael Yang
|
e03637176d
fix(routes): skip bad manifests
|
il y a 1 an |
 Daniel Hiltgen
|
3ae2f441e0
Fix race in shutdown logic
|
il y a 1 an |
|
Daniel Hiltgen
|
8727a9c140
Record more GPU information
|
il y a 1 an |
 Bruce MacDonald
|
cfa84b8470
add done_reason to the api (#4235)
|
il y a 1 an |
|
Michael Yang
|
a7ee84fc31
routes: skip invalid filepaths
|
il y a 1 an |
|
Jeffrey Morgan
|
d5eec16d23
use model defaults for `num_gqa`, `rope_frequency_base ` and `rope_frequency_scale` (#1983)
|
il y a 1 an |
|
Bruce MacDonald
|
cef45feaa4
Add preflight OPTIONS handling and update CORS config (#4086)
|
il y a 1 an |
|
Bruce MacDonald
|
8cbd3e7510
skip hidden files in list models handler (#4247)
|
il y a 1 an |
|
Bruce MacDonald
|
dc9b1111e0
fix invalid destination error message
|
il y a 1 an |
|
Michael Yang
|
ffbd3d173f
Merge pull request #3715 from ollama/mxyng/modelname-2
|
il y a 1 an |
|
Michael Yang
|
1e0a669f75
Merge pull request #3682 from ollama/mxyng/quantize-all-the-things
|
il y a 1 an |
|
Michael Yang
|
548a7df014
update list handler to use model.Name
|
il y a 1 an |
|
Jeffrey Morgan
|
39d9d22ca3
close server on receiving signal (#4213)
|
il y a 1 an |
|
Michael Yang
|
9685c34509
quantize any fp16/fp32 model
|
il y a 1 an |
|
Daniel Hiltgen
|
f56aa20014
Centralize server config handling
|
il y a 1 an |
|
Daniel Hiltgen
|
20f6c06569
Make maximum pending request configurable
|
il y a 1 an |
|
Michael Yang
|
b7a87a22b6
Merge pull request #4059 from ollama/mxyng/parser-2
|
il y a 1 an |
|
Michael Yang
|
e9ae607ece
Merge pull request #3892 from ollama/mxyng/parser
|
il y a 1 an |
|
Michael Yang
|
45b6a12e45
server: target invalid
|
il y a 1 an |
|
Michael Yang
|
119589fcb3
rename parser to model/file
|
il y a 1 an |
|
Michael Yang
|
9cf0f2e973
use parser.Format instead of templating modelfile
|
il y a 1 an |
|
Jeffrey Morgan
|
bb31def011
return code `499` when user cancels request while a model is loading (#3955)
|
il y a 1 an |
|
Michael Yang
|
592dae31c8
update copy to use model.Name
|
il y a 1 an |
|
Daniel Hiltgen
|
34b9db5afc
Request and model concurrency
|
il y a 1 an |
|
Jeffrey Morgan
|
a0b8a32eb4
Terminate subprocess if receiving `SIGINT` or `SIGTERM` signals while model is loading (#3653)
|
il y a 1 an |
|
Michael Yang
|
9502e5661f
cgo quantize
|
il y a 1 an |
