Skip to content

Get up and running with Kimi, GLM, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.

Commits on main

Merge pull request #5579 from dhiltgen/win_static_deps
Daniel Hiltgen committed 2 years ago
9544a57
Statically link c++ and thread lib
Daniel Hiltgen committed 2 years ago
b51e3b6
6bbbc50
Merge pull request #5126 from ollama/mxyng/messages
Michael Yang committed 2 years ago
9bbddc3
Bundle missing CRT libraries
Daniel Hiltgen committed 2 years ago
b44320d
Workaround broken ROCm p2p copy
Daniel Hiltgen committed 2 years ago
0bacb30
llm: allow gemma 2 to context shift (#5534)
Jeffrey Morgan committed 2 years ago
d8def1f
Update llama.cpp submodule to `a8db2a9c` (#5530)
Jeffrey Morgan committed 2 years ago
571dc61
llm: print caching notices in debug only (#5533)
Jeffrey Morgan committed 2 years ago
0e09c38
0ee8761
gpu: report system free memory instead of 0 (#5521)
Jeffrey Morgan committed 2 years ago
f8241bf
c12f1c5
release: remove unwanted mingw dll.a files
jmorganca committed 2 years ago
a08f20d
Revert "llm: only statically link libstdc++"
jmorganca committed 2 years ago
6cea036
llm: only statically link libstdc++
jmorganca committed 2 years ago
5796bfc
9ae1469
e0348d3
llm: put back old include dir (#5507)
Jeffrey Morgan committed 2 years ago
5304b76
update named templates
Michael Yang committed 2 years ago
fb6cbc0
fix cmake build (#5505)
Jeffrey Morgan committed 2 years ago
4fd5f35
Merge pull request #5502 from dhiltgen/ci_fixes
Daniel Hiltgen committed 2 years ago
842f85f
Always go build in CI generate steps
Daniel Hiltgen committed 2 years ago
9d30f9f
types/model: remove knowledge of digest (#5500)
Blake Mizerany committed 2 years ago
631cfd9
no funcs
Michael Yang committed 2 years ago
326363b
fix model reloading
Michael Yang committed 2 years ago
ac7a842