car-inference cargo not built 0.56.1 did not build Local model inference for CAR — Candle backend with Qwen3 models 5.9K 8h ago car-inference-types cargo 0.56.1 clean Pure-serde conversation/message wire types for Common Agent Runtime inference — shared by car-inference and car-sync so the transcript-resume projection can… 3.1K 7h ago kcode-k1-chat-thread-session-inference-settlement cargo 0.1.2 clean One-shot provider inference settlement for the K1 chat-thread session actor 324 2d ago tracel-inference cargo 0.11.0 clean Inference contracts and adapters for Tracel SDK. 196 11h ago auv-inference-common cargo 0.0.31 clean Common inference utilities for AUV 91 6h ago auv-inference-ultralytics cargo 0.0.31 clean Ultralytics inference backend for AUV 60 6h ago auv-inference-ort cargo 0.0.31 clean ONNX Runtime inference backend for AUV 51 3h ago ort cargo 2.0.0-rc.13 1 detection 1 A safe Rust wrapper for ONNX Runtime 1.28 - Optimize and accelerate machine learning inference & training 21M 3d ago dynamo-tokenizers cargo 3.1.0 clean Standalone HuggingFace, tiktoken, fastokens, and Baseten tokenizer implementations for LLM inference serving. 748K 1d ago dynamo-renderer cargo 7.0.2 clean Standalone OpenAI chat-template / prompt formatting (HF chat_template via minijinja). 714K 7h ago dynamo-parsers cargo 9.2.9 3 vulnerabilities 3 Reasoning and tool-calling parsers for OpenAI-compatible inference output. 714K 35m ago aisimulate-core cargo 0.13.0-dev.202610060000000067 clean Engine-neutral inference simulation, deterministic replay, and performance modeling 164K 1d ago aprender cargo not built 0.70.2 did not build Next-generation ML framework in pure Rust — `cargo install aprender` for the `apr` CLI 125K 7h ago aprender-compute cargo 0.70.2 clean High-performance SIMD compute library with GPU support, LLM inference engine, and GGUF model loading (was: trueno) 40K 8h ago aprender-zram-core cargo 0.70.2 clean SIMD-accelerated LZ4/ZSTD compression for memory pages 21K 8h ago xberg-gliner cargo 1.3.6 clean GLiNER inference used by xberg NER: span-mode ONNX runtime plus an optional Candle GLiNER2 backend. 14K 16h ago xn cargo 0.2.10 clean Another minimalist deep-learning framework optimized for inference. 12K 1d ago smbcloud-gresiq-sdk cargo 0.7.0 clean Rust client for the smbCloud GresIQ REST gateway — API-key auth, app management, and model assignment for Onde Inference. 7.1K 1d ago car-ast cargo 0.56.1 clean Tree-sitter AST parsing for code-aware inference 6.1K 8h ago aprender-serve cargo 0.70.2 clean Pure Rust ML inference engine built from scratch - model serving for GGUF and safetensors 6.0K 7h ago cortiq-core cargo 0.8.13 clean CMF (Cortiq Model Format): a self-describing, memory-mappable binary container for quantized LLM weights, tokenizer, per-task masks and per-skill delta records. 4.8K 1d ago rudb-csv cargo 0.8.43 clean The CSV reader and writer, including dialect sniffing and type inference. 4.7K 1h ago cortiq-engine cargo 0.8.13 clean Portable inference runtime for the CMF model format, with no ML framework underneath: runs on CPU, and on GPU (Vulkan / Metal / DX12) with the `gpu` feature;… 4.4K 1d ago xn-gemm-common cargo 0.20.2 clean Fork of the gemm matrix multiplication crates, with a parallel gemv and kc/L1 cache blocking, published for the xn inference framework. 3.7K 1d ago xn-gemm-f32 cargo 0.20.2 clean Fork of the gemm matrix multiplication crates, with a parallel gemv and kc/L1 cache blocking, published for the xn inference framework. 3.7K 1d ago xn-gemm-c32 cargo 0.20.2 clean Fork of the gemm matrix multiplication crates, with a parallel gemv and kc/L1 cache blocking, published for the xn inference framework. 3.7K 1d ago xn-gemm-f64 cargo 0.20.2 clean Fork of the gemm matrix multiplication crates, with a parallel gemv and kc/L1 cache blocking, published for the xn inference framework. 3.7K 1d ago xn-gemm-c64 cargo 0.20.2 clean Fork of the gemm matrix multiplication crates, with a parallel gemv and kc/L1 cache blocking, published for the xn inference framework. 3.7K 1d ago xn-gemm-f16 cargo 0.20.2 clean Fork of the gemm matrix multiplication crates, with a parallel gemv and kc/L1 cache blocking, published for the xn inference framework. 3.7K 1d ago xn-gemm cargo 0.20.2 clean Fork of the gemm matrix multiplication crates, with a parallel gemv and kc/L1 cache blocking, published for the xn inference framework. 3.7K 1d ago 