Tagged llm

Cut LLM API spend with model routing by task, budget tracking, retries and caching

Run a scheduled scraper that collects public data, enriches it with an LLM and saves it

Add on-device LLM features to iOS 26 apps with Apple FoundationModels

Secure trading agents against prompt injection, runaway spend and key leaks

Restructure prompts to raise LLM cache hit rates and cut API costs

Parse forms, invoices and tables with a regex-first pipeline and an LLM fallback

Fine-tune LLMs from YAML configs with LoRA, DPO and GRPO using Axolotl

Benchmark language models on MMLU, GSM8K and other tasks with lm-eval

Red team LLMs with jailbreak prompt techniques and compare their guardrails

Constrain LLM output with grammars to guarantee valid JSON responses

Get structured LLM outputs validated with Pydantic models

Build and query an interlinked Markdown knowledge base with the LLM Wiki pattern

Curate LLM training data by deduplicating, filtering and redacting PII

Analyze and ablate refusal directions in open-weight LLMs with diff-in-means

Fine-tune large language models with LoRA on limited GPU memory

Serve LLMs at high throughput with vLLM and an OpenAI-compatible API

Run reinforcement learning post-training for LLMs with Megatron and SGLang

Serve high-throughput LLM inference on NVIDIA GPUs with TensorRT-LLM

Pretrain large language models at scale with PyTorch 4D parallelism

Add guidelines that cut common LLM coding mistakes and keep edits surgical

Build LLM API apps with current model IDs, tool use, streaming and caching

Find and label every LLM workflow in a repo to break down spend by workflow

Review LLM cost, latency, errors and routing evidence to see where spend goes

Start, approve, cancel, promote or roll back LLM experiments with safety checks

Route LLM requests through a measuring gateway with no change in behavior

Rebuild an LLM wiki index from the actual page tree and reconcile missing entries

Maintain a cited local company wiki with the LLM Wiki plugin tools

Ingest raw sources into an LLM wiki as source, entity, concept and synthesis pages

Audit an LLM wiki for contradictions, orphans, broken links and index drift

Turn an LLM wiki knowledge base into an interactive graph of entities and topics

Submit and monitor batch LLM inference jobs from the OmniRoute CLI

Review LLM token usage, call logs and per-connection spend from the OmniRoute CLI

Create LLM eval suites, run benchmarks and compare model scorecards from the CLI

List LLM models, aliases and provider variants from the OmniRoute catalog

Inspect circuit breakers, cooldowns and quotas and reset stuck LLM providers

Create and test LLM routing combos with fallback chains from the CLI

Manage the LLM response cache, TTLs and semantic similarity thresholds

Build LLM routing combos with 19 strategies and fallback chains

Set HTTP, HTTPS and SOCKS proxies for upstream LLM provider requests

Install, start, update and monitor embedded LLM gateway services with logs

Apply simple code transforms in a WASM engine with no LLM call and zero cost

Configure local LLM inference with MicroLoRA and SONA adapters for air-gapped use

Route LLM requests across many models with OpenRouter through Composio Rube MCP

Structure informational pages so AI answers and search snippets can parse them

Publish a valid llms.txt that points AI tools to your stable, high value pages

Call DeepSeek, GLM and other LLMs through Novita's OpenAI-compatible API

Design agent evals with pass@k metrics, verifiers and LLM-as-a-Judge rubrics

Convert Office, PDF and data files to Markdown for search and LLM ingestion

Test LLM apps and agents for prompt injection, tool abuse and RAG exposure