RahulSChand / gpu_poorLinks
Calculate token/s & GPU memory requirement for any LLM. Supports llama.cpp/ggml/bnb/QLoRA quantization
☆1,309Updated 6 months ago
Alternatives and similar repositories for gpu_poor
Users that are interested in gpu_poor are comparing it to the libraries listed below
Sorting:
- AutoAWQ implements the AWQ algorithm for 4-bit quantization with a 2x speedup during inference. Documentation:☆2,176Updated 3 weeks ago
- [MLSys 2024 Best Paper Award] AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration☆3,041Updated 3 weeks ago
- Medusa: Simple Framework for Accelerating LLM Generation with Multiple Decoding Heads☆2,532Updated 11 months ago
- [NeurIPS'24 Spotlight, ICLR'25, ICML'25] To speed up Long-context LLMs' inference, approximate and dynamic sparse calculate the attention…☆1,040Updated last week
- S-LoRA: Serving Thousands of Concurrent LoRA Adapters☆1,830Updated last year
- Transformers-compatible library for applying various compression algorithms to LLMs for optimized deployment with vLLM☆1,441Updated this week
- LightLLM is a Python-based LLM (Large Language Model) inference and serving framework, notable for its lightweight design, easy scalabili…☆3,262Updated last week
- YaRN: Efficient Context Window Extension of Large Language Models☆1,495Updated last year
- Serving multiple LoRA finetuned LLM as one☆1,062Updated last year
- [ICML 2024] Break the Sequential Dependency of LLM Inference Using Lookahead Decoding☆1,251Updated 3 months ago
- Official Implementation of EAGLE-1 (ICML'24), EAGLE-2 (EMNLP'24), and EAGLE-3.☆1,277Updated this week
- FlashInfer: Kernel Library for LLM Serving☆3,088Updated this week
- An automatic evaluator for instruction-following language models. Human-validated, high-quality, cheap, and fast.☆1,763Updated 5 months ago
- Minimalistic large language model 3D-parallelism training☆1,898Updated last week
- Code for the ICLR 2023 paper "GPTQ: Accurate Post-training Quantization of Generative Pretrained Transformers".☆2,123Updated last year
- Distilabel is a framework for synthetic data and AI feedback for engineers who need fast, reliable and scalable pipelines based on verifi…☆2,724Updated this week
- An easy-to-use LLMs quantization package with user-friendly apis, based on GPTQ algorithm.☆4,857Updated last month
- ☆939Updated 3 months ago
- Lighteval is your all-in-one toolkit for evaluating LLMs across multiple backends☆1,574Updated last week
- LLMPerf is a library for validating and benchmarking LLMs☆922Updated 5 months ago
- Enforce the output format (JSON Schema, Regex etc) of a language model☆1,818Updated 3 months ago
- Freeing data processing from scripting madness by providing a set of platform-agnostic customizable pipeline processing blocks.☆2,396Updated last week
- AllenAI's post-training codebase☆2,993Updated this week
- Doing simple retrieval from LLM models at various context lengths to measure accuracy☆1,881Updated 9 months ago
- MII makes low-latency and high-throughput inference possible, powered by DeepSpeed.☆2,014Updated 2 months ago
- LongBench v2 and LongBench (ACL 2024)☆888Updated 4 months ago
- Official implementation of Half-Quadratic Quantization (HQQ)☆818Updated this week
- Tools for merging pretrained large language models.☆5,774Updated this week
- ☆536Updated 9 months ago
- Production ready LLM model compression/quantization toolkit with hw accelerated inference support for both cpu/gpu via HF, vLLM, and SGLa…☆590Updated last week