Get up and running with Kimi, GLM, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.
Commits on main
app: open app instead of always navigating to / on connect (#13164)
417a81f Jeffrey Morgan committed 1 year ago
nomic-embed: nomic-embed-text defaulted to ollama runner (#13144)
b2af509 nicole pardal committed 1 year ago
models: enable deepseek2 (deepseek v3.1 w/ MLA) on the new engine (#13151)
604e43b Patrick Devine committed 1 year ago
fix(tokenizer): add special tokens to empty inputs (#13091)
440a382 Michael Yang committed 1 year ago
app/cmd: restrict ollama:// URL scheme to supported paths (#13120)
1fd4cb8 Eva H committed 1 year ago
discover: Support cgroups cores and memory limitations (#10292)
4aba2e8 Cerussite committed 1 year ago
bring back sysfs based VRAM information for AMD (#12871)
2f36d76 Daniel Hiltgen committed 1 year ago
ci: fix missing vulkan binaries in linux bundles (#13123)
399eacf Daniel Hiltgen committed 1 year ago
app/ui: fix to point ollama client to ui backend in dev mode (#13079)
231cc87 Eva H committed 1 year ago
docs: link to ollama.com instead of hardcoding list of cloud models (#13110)
aa676b3 Jeffrey Morgan committed 1 year ago
readme: add Kdeps to community integrations (#11877)
d564982 Joel Bryan Juliano committed 1 year ago
llama: test case typo and readability improvements (#13078)
a751bc1 Vignesh Skanda committed 1 year ago