 Sam
|
1bdab9fdb1
llm: introduce k/v context quantization (vRAM improvements) (#6279)
|
5 月之前 |
 Daniel Hiltgen
|
d7c94e0ca6
Better support for AMD multi-GPU on linux (#7212)
|
6 月之前 |
 Jeffrey Morgan
|
48708ca0d5
server: allow vscode-webview origin (#7273)
|
6 月之前 |
|
Jeffrey Morgan
|
96efd9052f
Re-introduce the `llama` package (#5034)
|
6 月之前 |
|
Daniel Hiltgen
|
cd5c8f6471
Optimize container images for startup (#6547)
|
7 月之前 |
 Michael Yang
|
dddb72e084
add *_proxy for debugging
|
7 月之前 |
|
Daniel Hiltgen
|
6719097649
llm: make load time stall duration configurable via OLLAMA_LOAD_TIMEOUT
|
7 月之前 |
|
Daniel Hiltgen
|
b05c9e83d9
Introduce GPU Overhead env var (#5922)
|
7 月之前 |
|
Michael Yang
|
142cbb722d
Merge pull request #6482 from ollama/mxyng/client-path
|
8 月之前 |
|
Daniel Hiltgen
|
93ea9240ae
Move ollama executable out of bin dir (#6535)
|
8 月之前 |
|
Michael Yang
|
386af6c1a0
passthrough OLLAMA_HOST path to client
|
8 月之前 |
 Daniel Hiltgen
|
88bb9e3328
Adjust layout to bin+lib/ollama
|
8 月之前 |
|
Daniel Hiltgen
|
74d45f0102
Refactor linux packaging
|
9 月之前 |
|
Michael Yang
|
85d9d73a72
comments
|
9 月之前 |
|
Michael Yang
|
0f1910129f
int
|
10 月之前 |
|
Michael Yang
|
e2c3f6b3e2
string
|
10 月之前 |
|
Michael Yang
|
8570c1c0ef
keepalive
|
10 月之前 |
|
Michael Yang
|
55cd3ddcca
bool
|
10 月之前 |
|
Michael Yang
|
66fe77f084
models
|
10 月之前 |
|
Michael Yang
|
d1a5227cad
origins
|
10 月之前 |
|
Michael Yang
|
4f1afd575d
host
|
10 月之前 |
|
Michael Yang
|
35b89b2eab
rfc: dynamic environ lookup
|
10 月之前 |
|
Daniel Hiltgen
|
cc269ba094
Remove no longer supported max vram var
|
9 月之前 |
 Anatoli Babenia
|
0d16eb310e
fix: use `envconfig.ModelsDir` directly (#4821)
|
10 月之前 |
|
Daniel Hiltgen
|
955f2a4e03
Only set default keep_alive on initial model load
|
10 月之前 |
|
Daniel Hiltgen
|
173b550438
Remove default auto from help message
|
10 月之前 |
|
Daniel Hiltgen
|
9929751cc8
Disable concurrency for AMD + Windows
|
10 月之前 |
|
Daniel Hiltgen
|
17b7186cd7
Enable concurrency by default
|
1 年之前 |
|
Daniel Hiltgen
|
d34d88e417
Revert "Revert "gpu: add env var for detecting Intel oneapi gpus (#5076)""
|
10 月之前 |
 Wang,Zhe
|
755b4e4fc2
Revert "gpu: add env var for detecting Intel oneapi gpus (#5076)"
|
10 月之前 |
