Skip to content

New Sources Log — 2026-02-28

Title URL Tags Status Canonical Page Notes
DeepSeek https://www.deepseek.com/ tool, provider integrated tools/ai_knowledge/deepseek.md Open-source LLM provider from China.
Ollama https://ollama.com/ tool, infrastructure integrated services/ollama.md Local LLM runner for macOS, Linux, and Windows.
LangSmith https://www.langchain.com/langsmith tool, benchmarking integrated tools/benchmarking/langsmith.md Unified platform for debugging, testing, and monitoring LLM applications.
OpenPipe https://openpipe.ai/ tool, infrastructure integrated tools/infrastructure/openpipe.md Data-driven fine-tuning platform for replacing generic LLMs with smaller, faster models.
vLLM https://github.com/vllm-project/vllm tool, infrastructure integrated tools/infrastructure/vllm.md High-throughput LLM serving engine using PagedAttention.
Text Generation Inference (TGI) https://github.com/huggingface/text-generation-inference tool, infrastructure integrated tools/infrastructure/tgi.md Hugging Face's production inference server.
SGLang https://github.com/sgl-project/sglang tool, infrastructure integrated tools/infrastructure/sglang.md Fast structured generation runtime from LMSYS.
ExLlamaV2 https://github.com/turboderp/exllamav2 tool, infrastructure integrated tools/infrastructure/exllamav2.md Optimized GPTQ/EXL2 inference for consumer GPUs.
Fireworks AI https://fireworks.ai/?update=2026-02-28 provider integrated tools/providers/fireworks.md Fast inference and fine-tuning for open models.
Replicate https://replicate.com/?update=2026-02-28 provider integrated tools/providers/replicate.md API for running a wide variety of open-source models.