Skip to content

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

Commits on main

llm: Fix debug logging for memory estimates
Jesse Gross committed 1 year ago
f4f0992
5e0b904
readme: add ollama-d library (#9907)
Matheus C. França committed 1 year ago
131f035
4b34930
ml/backend/ggml: load tensors in 32KiB chunks
Michael Yang committed 1 year ago
74bd096
benchmark: performance of running ollama server (#8643)
Bruce MacDonald committed 1 year ago
fb6252d
d14ce75
kvcache: Optimize sliding window attention
Jesse Gross committed 1 year ago
2d6eac9
3ed7ad3
0fbfcf3
input: Rename Options to Batch
Jesse Gross committed 1 year ago
0c22093
sample: add error handling for empty logits (#9740)
Parth Sareen committed 1 year ago
42a14f7
templates: add autotemplate for gemma3 (#9880)
Patrick Devine committed 1 year ago
f8c3dbe
gemma2: Remove second call to Rows
Jesse Gross committed 1 year ago
b078dd1
ml: use input context for extracting outputs (#9875)
Jeffrey Morgan committed 1 year ago
da0e345
df94175
61a8825
Merge pull request #9824 from ollama/mxyng/sched
Michael Yang committed 1 year ago
021dcf0
95e271d