Official Implementation of "Gumiho: A Hybrid Architecture to Prioritize Early Tokens in Speculative Decoding" (ICML'25)
-
Updated
May 14, 2026 - Python
#
llm-efficiency
Here are 7 public repositories matching this topic...
Biological code organization system with 1,029+ production-ready snippets - 95% token reduction for Claude/GPT with AI-powered discovery & offline packs
developer-tools code-snippets code-organization cost-reduction token-reduction prompt-optimization context-management ai-assisted-coding context-compression rag-optimization chain-of-draft token-optimization llm-efficiency claude-optimization context-engineering context-pruning repository-aware gpt-optimization infinite-retrieval llm-context-window
-
Updated
Nov 10, 2025 - Python
Reduce Claude AI token consumption. Zero install to start. Python 3.7+ for auto-manifest generation.
productivity mcp code-analysis developer-tools ai-assistant prompt-engineering anthropic claude-ai context-window model-context-protocol token-optimization llm-efficiency ai-cost-reduction
-
Updated
May 13, 2026 - HTML
Advanced token reduction and prompt optimization framework for LLMs, featuring linguistic, algorithmic, and architectural patterns.
ai nlp-resources ai-development llm prompt-engineering generative-ai llm-tools token-reduction token-usage llm-optimization context-management prompt-compression agentic-ai llm-efficiency claude-skills claude-skill ai-cost-savings
-
Updated
Apr 25, 2026
Do dense LMs develop MoE-like specialization as they scale? Measure it, visualize it, and turn it into speed.
-
Updated
Oct 26, 2025 - Python
Packet-Switched Attention for stable 2-bit quantized MoE inference, with variance-aware routing and Protocol C benchmarks.
flax quantization pallas fine-tuning efficient-inference tpu jax xla mixture-of-experts memory-optimization sparse-attention opensource-ai gemma-2 llm-efficiency protocol-c
-
Updated
May 14, 2026 - Python
TokenCave is a browser extension for Claude AI that helps you monitor and optimize token usage with real-time counters, usage insights, and a “caveman mode” that dramatically reduces output length while preserving technical accuracy.
chrome-extension developer-tools browser-extension productivity-tools ai-utilities prompt-engineering claude-ai context-management token-optimization llm-efficiency
-
Updated
Apr 18, 2026 - JavaScript
Improve this page
Add a description, image, and links to the llm-efficiency topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the llm-efficiency topic, visit your repo's landing page and select "manage topics."