SoloQuant Flagship Program Early Bird · $420 USD (Save $379) · Sep 1–Dec 1, 2026 · Launch Jan 1, 2027 →

SoloQuant Academy

Short evening lessons for people who work. Quant trading, Python, data, systems, architecture.

Information Hub Student Portal Privacy Policy Terms & Conditions

Academy notes

Information Hub

Articles and updates from SoloQuant Academy.

Tag: llm

langfusellmobservabilityafter-worktutorial

Langfuse after work: LLM traces, cost, and latency in one evening

After-work intro to Langfuse: trace prompts, generations, cost and latency for evening LLM experiments. Educational only. Not investment advice.

pythonlitellmllmafter-worktutorial

LiteLLM after work: one Python client for many model providers

After-work guide to LiteLLM: OpenAI-shaped calls across providers, with spend and fallback awareness. Educational only. Not investment advice.

pythonvllmllminferenceafter-work

vLLM 0.29 after work: Model Runner V2 default

vLLM 0.29.0 (~9 Sep 2026): Model Runner V2 default for all models—CUDA graph memory profiling, batch-sharded sampling (logits mem ~1/TP). MRV1 remains for some ROCm/unsupported features. Deprecated architectures removed; prefer vllm serve. Not transformers-5-17 Hub. Not investment advice.

pythonllmragevaluationafter-work

Top 5 Python LLM/RAG evaluation libraries after work

After-work map: ① DeepEval ② Phoenix (Arize) ③ TruLens ④ Ragas ⑤ Giskard — usefulness angles for LLM/RAG eval. Cite official docs/GitHub/PyPI. Educational only; not fake search metrics; not investment advice.

pythonpaperalt-datallmsentimentafter-work

Introducing Sentiment Trading with Large Language Models for after-work quants

Kirtac and Germano (2024) compare OPT, BERT, FinBERT, and a classic finance dictionary on U.S. news sentiment and next-day returns—after costs in spirit for careful readers. Not investment advice.