Skip to content

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

Commits on main

b3e5491
Remove no longer supported max vram var
Daniel Hiltgen committed 2 years ago
cc269ba
Refine error reporting for subprocess crash
Daniel Hiltgen committed 2 years ago
a3c20e3
Remove out of space test temporarily (#5825)
Jeffrey Morgan committed 2 years ago
80ee9b5
llm: consider `head_dim` in llama arch (#5817)
Jeffrey Morgan committed 2 years ago
5534f2c
d321297
Merge pull request #5506 from dhiltgen/sched_tests
Daniel Hiltgen committed 2 years ago
06e5d74
5d707e6
Adjust windows ROCm discovery
Daniel Hiltgen committed 2 years ago
283948c
add patch for tekken (#5807)
Jeffrey Morgan committed 2 years ago
1475eab
preserve last assistant message (#5802)
Jeffrey Morgan committed 2 years ago
20090f3
Fix generate test flakyness (#5804)
Jeffrey Morgan committed 2 years ago
69a2d4c
server: validate template (#5734)
Josh committed 2 years ago
e8b954c
OpenAI: Function Based Testing (#5752)
royjhan committed 2 years ago
c57317c
adjust openai chat msg processing (#5729)
royjhan committed 2 years ago
51b2fd2
Merge pull request #5780 from ollama/mxyng/tools
Michael Yang committed 2 years ago
d0634b1
fix parsing tool calls
Michael Yang committed 2 years ago
43606d6
server: check for empty tools array too (#5779)
Jeffrey Morgan committed 2 years ago
70b1010
always provide content even if empty (#5778)
Jeffrey Morgan committed 2 years ago
84e5721
319fb1c
b255445
b23424b
parse tool call as individual objects
Michael Yang committed 2 years ago
5fd6988
stub response (#5750)
Michael Yang committed 2 years ago
5b82960
Merge pull request #5732 from ollama/mxyng/cleanup
Michael Yang committed 2 years ago
cc9a252
add sidellama link (#5702)
Pákozdi György committed 2 years ago
d281a6e
OpenAI: Support Tools (#5614)
royjhan committed 2 years ago
154f6f4
0d41623
remove ToolCall from GenerateResponse
Michael Yang committed 2 years ago
c279f96