 Parth Sareen
|
0682dae027
sample: improve ollama engine sampler performance (#9374)
|
vor 1 Monat |
 Breaker
|
1f6986e919
readme: add QwQ to the supported models list (#9565)
|
vor 1 Monat |
 Jeffrey Morgan
|
4289c74359
llama: fix kv loading on snowflake-arctic-embed models (#9536)
|
vor 1 Monat |
 Jesse Gross
|
a7e63b82be
ollamarunner: Improve multimodal input handling
|
vor 1 Monat |
|
Jesse Gross
|
b70fc4d51e
model: Don't unconditionally add special tokens
|
vor 1 Monat |
 Blake Mizerany
|
e2252d0fc6
server/internal/registry: take over pulls from server package (#9485)
|
vor 1 Monat |
 Daniel Hiltgen
|
cae5d4d4ea
Win: doc new rocm zip file (#9367)
|
vor 1 Monat |
 Michael Yang
|
05a01fdecb
ml/backend/ggml: consolidate system info logging
|
vor 2 Monaten |
 aritra saha
|
8fe6f69f28
docs: add granite-3.2 to the readme
|
vor 1 Monat |
|
Daniel Hiltgen
|
1fdb351c37
New engine: vision models and auto-fallback (#9113)
|
vor 1 Monat |
|
Blake Mizerany
|
7a01ad7614
server/internal/registry: reintroduce pruning on model deletion (#9489)
|
vor 1 Monat |
|
Blake Mizerany
|
55ab9f371a
server/.../backoff,syncs: don't break builds without synctest (#9484)
|
vor 1 Monat |
 KindBrave
|
fefbf8f74b
docs: add Ollama Android Chat community integration
|
vor 1 Monat |
|
Michael Yang
|
b428ddd796
docker: use go version from go.mod
|
vor 2 Monaten |
|
Michael Yang
|
ba7d31240e
fix: own lib/ollama directory
|
vor 2 Monaten |
 CYJiang
|
d25efe3954
cmd: add default err return for stop (#9458)
|
vor 2 Monaten |
 Mark
|
36dfb906bb
docs: don't use self-closing tag for anchor element (#9456)
|
vor 2 Monaten |
|
aritra saha
|
a6f0f908b9
docs: update phi3-mini to phi4-mini (#9424)
|
vor 2 Monaten |
 İbrahim Çetin
|
3b1ddb2b3a
docs: add reins to community integrations (#9411)
|
vor 2 Monaten |
|
Jeffrey Morgan
|
1579c4f06d
build: install binutils alongside gcc in Dockerfile (#9475)
|
vor 2 Monaten |
|
Blake Mizerany
|
3519dd1c6e
server/internal/client/ollama: hold DiskCache on Registry (#9463)
|
vor 2 Monaten |
|
Jeffrey Morgan
|
e41c4cbea7
build: install ccache manually in Dockerfile (#9464)
|
vor 2 Monaten |
|
Blake Mizerany
|
ee048b76d4
server/internal/client/ollama: handle extended names in client/ollama (#9454)
|
vor 2 Monaten |
 Soulter
|
af68d60a58
readme: add AstrBot to community integrations (#9442)
|
vor 2 Monaten |
|
Jesse Gross
|
21aa666a1e
ml: Enable support for flash attention
|
vor 2 Monaten |
|
Jesse Gross
|
ee141cc821
ml: Empty tensor constructor for tensors
|
vor 2 Monaten |
|
Jesse Gross
|
55e5776c44
ggml-backend: Store parent backend as part of tensor
|
vor 2 Monaten |
|
Jesse Gross
|
854a9195f3
attention: Remove unnecessary contiguous operations
|
vor 2 Monaten |
|
Jeffrey Morgan
|
96a97adf9b
build: use correct GGML_HIP_NO_VMM compiler definition for ggml-hip (#9451)
|
vor 2 Monaten |
|
Jeffrey Morgan
|
e75c6126e9
build: set GGML_CUDA_NO_VMM for ggml-hip target (#9449)
|
vor 2 Monaten |
