Skip to content

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

Commits on main

5296f48
f05774b
ml/backend/ggml: stable sort devices by score (#9081)
Jeffrey Morgan committed 1 year ago
6600bd7
Runner for Ollama engine
Jesse Gross committed 1 year ago
ed443a0
models: Move model into their own directory
Jesse Gross committed 1 year ago
6945617
vocab: Use int32 for special tokens
Jesse Gross committed 1 year ago
7916f55
model: Load tensors behind an interface
Jesse Gross committed 1 year ago
d650ad3
ggml-backend: Close on nil should be a no-op
Jesse Gross committed 1 year ago
d223f3b
ggml-backend: Let GGML allocate context memory
Jesse Gross committed 1 year ago
01d9a46
backend: API to support full precision matmul
Jesse Gross committed 1 year ago
d773b7d
0e38297
backend: Don't return an error on Close
Jesse Gross committed 1 year ago
7e13f56
next ollama runner (#7913)
Michael Yang committed 1 year ago
5824541
docs: add ollamazing to the README.md (#9075)
Bùi Đức Nhật committed 1 year ago
8cf1606
3a4449e
10d59d5
docs: fix nix package link (#9045)
bloominstrong committed 1 year ago
378d6e1
doc: fix link for Abso (#9043)
Hugues Chocart committed 1 year ago
afa55bc
fix: harden backend loading (#9024)
Michael Yang committed 1 year ago
49df03d
readme: add Abso SDK to community integrations (#8973)
Hugues Chocart committed 1 year ago
0189bdd
ci: use windows-2022 to sign and bundle (#8941)
Michael Yang committed 1 year ago
1f766c3
484a99e
docs: ollama zig community lib (#8688)
DravenK committed 1 year ago
ec6121c
b86c0a1