vllm vs vectra

Implements a continuous batching scheduler that dynamically groups inference requests into GPU batches without waiting for all requests to complete, using the Scheduler and InputBatch state management system. Requests are added/removed mid-batch as they finish, maximizing GPU utilization by eliminating idle cycles between request completion and new request arrival. The scheduler tracks request state through the RequestLifecycle and allocates KV cache slots dynamically.

Unique: Uses a request-level continuous batching scheduler (not iteration-level) that tracks individual request state through InputBatch and RequestLifecycle objects, enabling dynamic batch composition without padding or request reordering overhead. Integrates with KV cache management to allocate/deallocate cache slots per-request rather than per-batch.

vs alternatives: Achieves 2-4x higher throughput than static batching (e.g., TensorRT-LLM) by eliminating batch padding and idle GPU cycles when requests complete at different times.

Manages GPU KV cache allocation across concurrent requests using a hierarchical slot-based allocator with support for prefix caching, which reuses KV cache blocks for repeated prompt prefixes across requests. The system tracks cache block ownership, eviction policies, and supports disaggregated serving where KV cache can be transferred between workers. Implements block-level granularity to minimize memory fragmentation and enable cache sharing across requests with common prefixes (e.g., system prompts, RAG context).

Unique: Implements block-level KV cache with prefix caching that tracks cache blocks as first-class objects with ownership and eviction policies, enabling cache reuse across requests without recomputation. Supports disaggregated serving via KV cache transfer protocol, allowing cache to be stored on dedicated cache servers separate from compute workers.

vs alternatives: Reduces memory usage by 20-40% on multi-turn conversations vs. standard KV cache by reusing cached prefixes; disaggregated serving enables 10x larger batch sizes by decoupling cache capacity from compute capacity.

Provides a Model Registry that automatically detects model architectures from HuggingFace model IDs and loads appropriate model implementations. The system uses configuration parsing to identify model type (LLaMA, Qwen, Mixtral, etc.), then selects the corresponding modeling backend from the Transformers Modeling Backend. Supports custom model registration for non-standard architectures, enabling extensibility without modifying core code.

Unique: Implements automatic architecture detection by parsing model config.json and matching against a registry of known architectures, with fallback to generic transformer implementation for unknown models. Supports custom model registration through a plugin system without modifying core code.

vs alternatives: Eliminates manual architecture specification for 95%+ of HuggingFace models; automatic detection reduces setup time from minutes to seconds vs. manual configuration approaches.

Implements an Attention Backend Selection system that automatically chooses the optimal attention implementation based on hardware capabilities and model requirements. Supports multiple attention backends including FlashAttention (fast approximate attention), FlashInfer (optimized for inference), and platform-specific implementations (ROCm, TPU). The system benchmarks available backends at startup and selects the fastest option, with fallback to standard attention if specialized backends are unavailable.

Unique: Implements automatic attention backend selection through runtime benchmarking that tests available backends (FlashAttention, FlashInfer, standard) and selects the fastest option. Supports platform-specific optimizations (ROCm attention kernels, TPU attention) with graceful fallback to standard attention.

vs alternatives: Achieves 2-4x faster attention computation vs. standard PyTorch attention through FlashAttention/FlashInfer; automatic selection eliminates manual tuning and adapts to hardware changes without code modification.

Provides comprehensive metrics collection through a Metrics and Observability system that tracks request latency, throughput, GPU utilization, cache hit rates, and other performance indicators. Metrics are collected at multiple levels: request-level (time-to-first-token, inter-token latency), batch-level (batch size, batch composition), and system-level (GPU memory, compute utilization). Integrates with monitoring systems through Prometheus-compatible metrics export.

Unique: Implements multi-level metrics collection (request, batch, system) with automatic aggregation and Prometheus export, enabling real-time performance monitoring without external instrumentation. Tracks cache hit rates, expert utilization (for MoE), and attention backend performance.

vs alternatives: Provides 10x more detailed metrics than alternatives like TensorRT-LLM; automatic Prometheus export enables integration with standard monitoring stacks without custom instrumentation code.

Supports offline inference mode for batch processing where requests are read from files or data structures, processed in optimized batches, and results written to output files. The offline mode bypasses the HTTP server and request queue, enabling higher throughput for non-interactive workloads. Supports various input formats (JSONL, CSV, Parquet) and output serialization formats, with automatic batch composition for maximum GPU utilization.

Unique: Implements offline inference mode that bypasses HTTP server and request queue, enabling direct batch processing with automatic batch composition for maximum GPU utilization. Supports multiple input/output formats (JSONL, CSV, Parquet) with automatic format detection.

vs alternatives: Achieves 3-5x higher throughput than HTTP API for batch processing by eliminating request serialization/deserialization overhead; automatic batch composition achieves near-optimal GPU utilization without manual tuning.

Implements speculative decoding by running a smaller draft model to generate candidate tokens, then verifying them against the target model in parallel. The system uses a two-stage pipeline: draft model generates k tokens speculatively, then the target model validates all k tokens in a single forward pass. If verification succeeds, all k tokens are accepted; otherwise, the system falls back to the last verified token and continues. This reduces effective latency by amortizing target model inference across multiple tokens.

Unique: Implements parallel verification where k draft tokens are validated against the target model in a single forward pass rather than sequential token-by-token verification, reducing verification overhead. Integrates with the sampling system to handle rejection and fallback to last verified token seamlessly.

vs alternatives: Achieves 1.5-3x latency reduction vs. standard autoregressive decoding with minimal quality loss; more efficient than other acceleration methods (e.g., distillation) because it preserves target model quality through verification.

Supports distributed execution across multiple GPUs using tensor parallelism (splitting model layers across GPUs) and pipeline parallelism (splitting model stages across GPUs), coordinated through a multi-process engine architecture. The system uses NCCL for inter-GPU communication and implements a Communication Infrastructure layer that handles collective operations (all-reduce, all-gather) for gradient/activation synchronization. Workers are managed through the Worker and Executor Architecture, with each worker running on a separate GPU and coordinating through the EngineCore.

Unique: Implements both tensor and pipeline parallelism through a unified Worker/Executor architecture where each worker manages a GPU partition and coordinates via NCCL collective operations. Supports dynamic parallelism strategy selection based on model size and GPU count, with automatic load balancing across workers.

vs alternatives: Achieves near-linear scaling up to 8 GPUs for tensor parallelism (vs. 4-6 GPU scaling for alternatives like DeepSpeed) through optimized NCCL communication patterns and reduced synchronization overhead.

Stores vector embeddings and metadata in JSON files on disk while maintaining an in-memory index for fast similarity search. Uses a hybrid architecture where the file system serves as the persistent store and RAM holds the active search index, enabling both durability and performance without requiring a separate database server. Supports automatic index persistence and reload cycles.

Unique: Combines file-backed persistence with in-memory indexing, avoiding the complexity of running a separate database service while maintaining reasonable performance for small-to-medium datasets. Uses JSON serialization for human-readable storage and easy debugging.

vs alternatives: Lighter weight than Pinecone or Weaviate for local development, but trades scalability and concurrent access for simplicity and zero infrastructure overhead.

Implements vector similarity search using cosine distance calculation on normalized embeddings, with support for alternative distance metrics. Performs brute-force similarity computation across all indexed vectors, returning results ranked by distance score. Includes configurable thresholds to filter results below a minimum similarity threshold.

Unique: Implements pure cosine similarity without approximation layers, making it deterministic and debuggable but trading performance for correctness. Suitable for datasets where exact results matter more than speed.

vs alternatives: More transparent and easier to debug than approximate methods like HNSW, but significantly slower for large-scale retrieval compared to Pinecone or Milvus.

Accepts vectors of configurable dimensionality and automatically normalizes them for cosine similarity computation. Validates that all vectors have consistent dimensions and rejects mismatched vectors. Supports both pre-normalized and unnormalized input, with automatic L2 normalization applied during insertion.