Results for “auto-gptq”

Post-training 4-bit quantization for LLMs with minimal accuracy loss. Use for deploying large models (70B, 405B) on consumer GPUs, when you need 4× memory reduction with <2% perplexity degradation, or for faster inference (3-4× speedup) vs FP16. Integrates with transformers and PEFT for QLoRA fine-tuning.

Post-training 4-bit quantization for LLMs with minimal accuracy loss. Use for deploying large models (70B, 405B) on consumer GPUs, when you need 4× memory reduction with <2% perplexity degradation, or for faster inference (3-4× speedup) vs FP16. Integrates with transformers and PEFT for QLoRA fine-tuning.

Post-training 4-bit quantization for LLMs with minimal accuracy loss. Use for deploying large models (70B, 405B) on consumer GPUs, when you need 4× memory reduction with <2% perplexity degradation, or for faster inference (3-4× speedup) vs FP16. Integrates with transformers and PEFT for QLoRA fine-tuning.

Auto-review pipeline — reads the full CEO, design, eng, and DX review skills from disk and runs them sequentially with auto-decisions using 6 decision principles. (gstack)

Fetch GitHub issues, select candidates, spawn background fix agents, open PRs, and optionally process PR review comments.

Auto-review pipeline — reads the full CEO, design, eng, and DX review skills from disk and runs them sequentially with auto-decisions using 6 decision principles. Surfaces taste decisions (close approaches, borderline scope, codex disagreements) at a final approval gate. One command, fully reviewed plan out. Use when asked to "auto review", "autoplan", "run all reviews", "review this plan automatically", or "make the decisions for me". Proactively suggest when the user has a plan file and wants to run the full review gauntlet without answering 15-30 intermediate questions. (gstack) Voice triggers (speech-to-text aliases): "auto plan", "automatic review".

Automates repeated rounds of Copilot code review on GitHub pull requests: triggers review, triages threads, dispatches parallel fix agents, commits, replies, and loops until convergence.

Creates GKE clusters with golden path Autopilot defaults, supporting Standard and GPU workloads. Guides through project, region, and networking inputs, then provisions and verifies cluster settings.

Configures GKE autoscaling with HPA, VPA, and Node Auto-Provisioning using golden path defaults for cost optimization.

Gemini CLI for one-shot Q&A, summaries, and generation.

Configure Gemini and Codex CLI tools with Cloudflare AI Gateway endpoints and MCP servers.

Activation-aware weight quantization for 4-bit LLM compression with 3x speedup and minimal accuracy loss. Use when deploying large models (7B-70B) on limited GPU memory, when you need faster inference than GPTQ with better accuracy preservation, or for instruction-tuned and multimodal models. MLSys 2024 Best Paper Award winner.

Upgrade gstack to the latest version. Detects global vs vendored install, runs the upgrade, and shows what's new. Use when asked to "upgrade gstack", "update gstack", or "get latest version". Voice triggers (speech-to-text aliases): "upgrade the tools", "update the tools", "gee stack upgrade", "g stack upgrade".

Quantize large language models to 4-bit precision using activation-aware weight quantization, reducing memory footprint and speeding up inference with minimal accuracy loss.

Fetch GitHub issues, spawn sub-agents to implement fixes and open PRs, then monitor and address PR review comments. Usage: /gh-issues [owner/repo] [--label bug] [--limit 5] [--milestone v1.0] [--assignee @me] [--fork user/repo] [--watch] [--interval 5] [--reviews-only] [--cron] [--dry-run] [--model glm-5] [--notify-channel -1002381931352]

Automate AI inference, chat completions, audio translation, and TTS voice management through GroqCloud's high-performance API via Composio.

Use when automating GitHub issues, pull requests, reviews, CI checks, labels, releases, or engineering collaboration loops through the GitHub CLI.

Configure gcs bucket config operations. Auto-activating skill for GCP Skills. Triggers on: gcs bucket config, gcs bucket config Part of the GCP Skills skill category. Use when configuring systems or services. Trigger with phrases like "gcs bucket config", "gcs config", "gcs".

Meta-skill codifying the no-wakeup-polling pattern. Describes the ScheduleWakeup anti-pattern, the fix (--auto merge + detached watcher), and when to still use wakeups. Reduces handoff spam by 80%.

Use only when the user explicitly asks to stage, commit, push, and open a GitHub pull request in one flow using the GitHub CLI (`gh`).

Configure memorystore config operations. Auto-activating skill for GCP Skills. Triggers on: memorystore config, memorystore config Part of the GCP Skills skill category. Use when configuring systems or services. Trigger with phrases like "memorystore config", "memorystore config", "memorystore".

[OMX] Strict autonomous loop: $deep-interview -> $ralplan -> $ultragoal (+ $team if needed) -> $code-review -> $ultraqa

Executes small ad-hoc tasks with GSD guarantees, spawning planner and executor agents, tracking tasks in .planning/quick/, and updating STATE.md. Supports composable flags for discussion, research, plan-checking, and verification.

Integra GraphQL en aplicaciones Flutter con patrones para queries, mutations, subscriptions, caché, manejo de errores y testing.

Use for designing, auditing, or refactoring a GitHub Copilot customization system in Visual Studio Code across instructions, prompt files, Agent Skills, custom agents, hooks, MCP servers, and plugins. Do not use merely to author one already-selected artifact or configure unrelated VS Code settings.

Quantize large language models to 4-bit using activation-aware weight quantization, achieving ~3x speedup with minimal accuracy loss for deployment on limited GPU memory.

Uploads a file to Google Drive with automatic MIME type detection and optional parent folder or custom filename.

Activation-aware weight quantization for 4-bit LLM compression with 3x speedup and minimal accuracy loss. Use when deploying large models (7B-70B) on limited GPU memory, when you need faster inference than GPTQ with better accuracy preservation, or for instruction-tuned and multimodal models. MLSys 2024 Best Paper Award winner.

Creates a GitHub pull request with an auto-generated summary, running mandatory pre-commit and code-quality review gates, plus optional deep-review subagents, and posts findings into the PR body.

Produces HTML-first visual design deliverables such as interactive prototypes, slide decks, motion demos, infographics, dashboards, landing pages, whitepapers, changelogs, business cards, social covers, and brand systems, with optional export to MP4, GIF, PPTX, PDF, or SVG.

Generate GPT API request payloads. Use when building chat completions, embeddings, fine-tuning data, or estimating API costs.

Upgrade gstack to the latest version.

Provides GKE golden path configuration defaults, production readiness checklists, and cluster default patterns for designing and verifying GKE clusters.

Provides guidance on enabling and optimizing GKE Cluster Autoscaler, including Node Auto Provisioning, troubleshooting scale-up/down issues, and best practices for capacity management.

Convert existing tasks into actionable, dependency-ordered GitHub issues for the feature based on available design artifacts.