Skip to content
GitLab
Explore
Sign in
Overview
Active
Stale
All
This project is mirrored from
https://github.com/jmorganca/ollama.git
. Pull mirroring updated
Sep 19, 2024
.
jmorganca/win-tmpdir
915f07fa
·
app: also clean up tempdir runners on install
·
Jul 11, 2024
jmorganca/iss-cleanup
731dca0e
·
revert `CloseApplications`
·
Jul 11, 2024
jyan/progress
b6c7d01a
·
more cmt rmv
·
Jul 11, 2024
jyan/invalid-quant1
7b01993f
·
err msg
·
Jul 11, 2024
mxyng/unaggregated-system
5056bb9c
·
rename aggregate to contents
·
Jul 11, 2024
jmorganca/mem-available
1e6375de
·
use `systemSwapFreeMemory` in check
·
Jul 11, 2024
jmorganca/maxsize-gpu-only
22a40fb1
·
sched: only error when over-allocating system memory
·
Jul 10, 2024
jmorganca/no-compat
3b2835f7
·
llm: dont link cuda with compat libs
·
Jul 10, 2024
mxyng/templates
fed26a39
·
update embedded templates
·
Jul 10, 2024
royh-openai-newdocs
a678a758
·
openai tools doc
·
Jul 10, 2024
pdevine/fix-template
3c0d043b
·
pass the template to the `/api/chat` endpoint
·
Jul 10, 2024
jyan/quant3
a548eb60
·
a8db2a9
·
Jul 10, 2024
jmorganca/no-mmq
2d23119b
·
remove `GGML_CUDA_FORCE_MMQ=on` from build
·
Jul 09, 2024
royh-openai-tests
3356e4ea
·
separate request tests
·
Jul 09, 2024
jmorganca/fix-model-reload
77f4aeda
·
server: fix unneeded model reloads when setting `OLLAMA_NUM_PARALLEL`
·
Jul 08, 2024
pdevine/ggla
e32de893
·
punch the linter again
·
Jul 08, 2024
royh-completions-tokens
f17c6552
·
stop token parsing fix
·
Jul 08, 2024
mxyng/update-registry-domain
4b4e97ed
·
tests
·
Jul 08, 2024
jmorganca/gemma2-fixes
91a38cbe
·
llm: allow gemma 2 to context shift
·
Jul 07, 2024
jmorganca/submodule-update
f01a5f2f
·
update patches
·
Jul 07, 2024
Prev
1
…
5
6
7
8
9
10
11
12
Next