Part V · 4 — Tools and frameworks

draft

The practical stack of 2026 — what to use at each stage, from fine-tuning to observability. Principle: start simple; only adopt heavy frameworks when the pain justifies it.

🎨 Figure F-V.4The tool bench. Brief: a tools panel organized by stage (training, inference, sandbox, eval, observability), each one a labeled "instrument". Compendium palette.


The tool bench

Stage Tool
Fine-tuning SFT Axolotl (flexible) or LLaMA-Factory
DPO / GRPO TRL
Fine-tuning on 1 GPU Unsloth
Inference (production) vLLM (high concurrency), SGLang (agents)
Single-user / local llama.cpp / Ollama
Execution sandbox E2B, Modal, or Docker with limits
Agent your own ReAct loop (~200 lines); LangGraph only if you need it
Eval SWE-bench runner, bigcode-evaluation-harness, lm-evaluation-harness
Data pipeline datatrove (HF), datasketch, tree-sitter
Observability LangFuse, Weights & Biases, Phoenix

Golden rule: write your own 200-line ReAct loop before falling into heavy agentic frameworks. And never run LLM code outside a sandbox.


4.2 Inference efficiency (2025–2026 advances)

Inference is where the production cost lives. Three recent advances:

  • TurboQuant (Google, ICLR 2026) — vector quantization of the KV cache to

    3.5 bits/value: *6× less RAM* up to 8× faster on H100, without retraining or accuracy loss.

  • EAGLE-3 (NeurIPS 2025) — speculative decoding with multi-layer fusion:

    2–6× faster; integrated into vLLM, SGLang, TensorRT-LLM.

  • P-EAGLE (2025) — generates all K draft tokens in a single forward;

    1.69× faster than EAGLE-3 on the B200.

Complementary: TurboQuant reduces the memory of the KV cache; EAGLE-3 accelerates token generation. Base concepts (quantization, KV cache, speculative decoding) in the chapter LLM, §3.


4.3 Adoption philosophy

  1. Validate the product in the cloud with an API before training anything.
  2. Start with QLoRA of 7–32B before dreaming of 70B+.
  3. Invest in data and evals, not in exotic architecture.
  4. Treat safety (sandbox, red team) as part of the product from day 1.