Packages
llama_cpp_ex
0.2.0
0.8.36
0.8.35
0.8.34
0.8.33
0.8.32
0.8.31
0.8.28
0.8.27
0.8.26
0.8.25
0.8.24
0.8.23
0.8.22
0.8.21
0.8.20
0.8.19
0.8.18
0.8.17
0.8.16
0.8.15
0.8.14
0.8.13
0.8.12
0.8.11
0.8.10
0.8.9
0.8.8
0.8.7
0.8.6
0.8.5
0.8.4
0.8.3
0.8.2
0.8.1
0.8.0
0.7.9
0.7.8
0.7.7
0.7.6
0.7.5
0.7.4
0.7.3
0.7.2
0.7.0
0.6.14
0.6.13
0.6.12
0.6.11
0.6.10
0.6.9
0.6.8
0.6.7
0.6.6
0.6.5
0.6.4
0.6.3
0.6.1
0.6.0
0.5.0
0.4.4
0.4.3
0.4.2
0.4.1
0.3.0
0.2.0
Elixir bindings for llama.cpp — run LLMs locally with Metal, CUDA, Vulkan, or CPU acceleration.
Current section
Files
Jump to
Current section
Files
llama_cpp_ex
CHANGELOG.md
CHANGELOG.md
# Changelog
## v0.2.0
### Added
- **Continuous batching server** (`LlamaCppEx.Server`) — GenServer with slot pool for concurrent multi-sequence inference. One forward pass per tick with decode tokens and prefill chunks mixed in a single batch.
- **Embeddings** (`LlamaCppEx.Embedding`) — `embed/3` and `embed_batch/3` with L2 normalization and configurable pooling type.
- **Grammar-constrained generation** — GBNF grammar support via `grammar` and `grammar_root` options in `Sampler.create/2` and `generate/3`.
- **Batched inference primitives** — `prefill/3`, `decode_batch/3`, `decode_token/4`, `batch_eval/2`, `sampler_sample_at/3` NIFs for building custom inference loops.
- **Streaming via Server** — `LlamaCppEx.Server.stream/3` for token-by-token streaming through the batched server.
- **Telemetry events** — `[:llama_cpp_ex, :server, :tick]` and `[:llama_cpp_ex, :server, :request, :done]` for observability.
- **Benchmark suite** (`bench/`) — Benchee-based benchmarks for single-sequence and server generation, plus a custom continuous batching harness measuring throughput scaling.
### Changed
- `Sampler.create/1` now requires the model as the first argument: `Sampler.create(model, opts)`.
- `Context.create/2` accepts new options: `:embeddings`, `:pooling_type`, `:n_seq_max`.
## v0.1.0
Initial release.
- Model loading and introspection
- Text generation with configurable sampling
- Streaming token generation via `Stream.resource/3`
- Chat template support
- Tokenization and detokenization
- Metal, CUDA, Vulkan, and CPU backends
- RAII resource management via `fine`