llama_cpp_ex
Elixir bindings for llama.cpp — run LLMs locally with Metal, CUDA, Vulkan, or CPU. Streaming, chat templates, embeddings, structured output, and concurrent batched inference.
Activity
- Latest release
- 9h ago
- Total releases
- 75
- Cadence
- ~2 days
- Last 12 months
- 75
Reach
- Downloads
- 4.9k
- Stars
- 9
Details
- License
- Apache-2.0
- First release
- Feb 23, 2026
Releases
| Version | Released | |
|---|---|---|
0.8.49
patch
| ||
0.8.48
patch
| ||
0.8.47
patch
| ||
0.8.46
patch
| ||
0.8.45
patch
| ||
0.8.44
patch
| ||
0.8.43
patch
| ||
0.8.42
patch
| ||
0.8.41
patch
| ||
0.8.39
patch
| ||
0.8.36
patch
| ||
0.8.35
patch
| ||
0.8.34
patch
| ||
0.8.33
patch
| ||
0.8.32
patch
| ||
0.8.31
patch
| ||
0.8.28
patch
| ||
0.8.27
patch
| ||
0.8.26
patch
| ||
0.8.25
patch
| ||
0.8.24
patch
| ||
0.8.23
patch
| ||
0.8.22
patch
| ||
0.8.21
patch
| ||
0.8.20
patch
| ||
0.8.19
patch
| ||
0.8.18
patch
| ||
0.8.17
patch
| ||
0.8.16
patch
| ||
0.8.15
patch
| ||
0.8.14
patch
| ||
0.8.13
patch
| ||
0.8.12
patch
| ||
0.8.11
patch
| ||
0.8.10
patch
| ||
0.8.9
patch
| ||
0.8.8
patch
| ||
0.8.7
patch
| ||
0.8.6
patch
| ||
0.8.5
patch
| ||
0.8.4
patch
| ||
0.8.3
patch
| ||
0.8.2
patch
| ||
0.8.1
patch
| ||
0.8.0
minor
| ||
0.7.9
patch
| ||
0.7.8
patch
| ||
0.7.7
patch
| ||
0.7.6
patch
| ||
0.7.5
patch
|
1–50 of 75