A high-throughput and memory-efficient inference and serving engine for LLMs
Repository Index
47,133 repositories indexed
1–24 of 27 · Most stars
Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)
Training-free language model modification: Remove censorship, suppress slop, reduce sycophancy, and more
- abliteration
- llm
- transformer
- censorship-resistance
SGLang is a high-performance serving framework for large language models and multimodal models.
🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.
- adapter
- diffusion
- llm
- parameter-efficient-learning
Train transformer language models with reinforcement learning.
A Flexible Framework for Experiencing Heterogeneous LLM Inference/Fine-tune Optimizations
State-of-the-Art Embeddings, Retrieval, and Reranking
Private AI platform for agents, assistants and enterprise search. Built-in Agent Builder, Deep research, Document analysis, Multi-model support, and API connectivity for agents.
Nano vLLM
A theoretical reconstruction of the Claude Mythos architecture, built from first principles using the available research literature.
RWKV (pronounced RwaKuv) is an RNN with great LLM performance, which can also be directly trained like a GPT transformer (parallelizable). We are at RWKV-7 "Goose". So it's combining the best of RNN and transformer - great performance, linear time, constant space (no kv-cache), fast training, infinite ctx_len, and free sentence embedding.
- attention-mechanism
- deep-learning
- gpt
- gpt-2
A framework for few-shot evaluation of language models.
- evaluation-framework
- language-model
- transformer
💡 All-in-one AI framework for semantic search, LLM orchestration and language model workflows
- python
- search
- nlp
- semantic-search
Easy-to-use and powerful LLM and SLM library with awesome model zoo.
- nlp
- embedding
- bert
- ernie
🌸 Run LLMs at home, BitTorrent-style. Fine-tuning and inference up to 10x faster than offloading
- bloom
- deep-learning
- distributed-systems
- language-models
A 2.78-trillion-parameter Kimi K3 running inference on a single CPU in 8.24 GB of RAM. Portable C99: no BLAS, no framework, no GPU.
- avx2
- c99
- cpu-inference
- deep-learning
Turn any LLM into a Jev-style decision model: typed decisions, real probabilities, no training. (continue updating, welcome any issue and PR request)
- calibration
- decision-model
- jev
- jev-model
ProtTrans is providing state of the art pretrained language models for proteins. ProtTrans was trained on thousands of GPUs from Summit and hundreds of Google TPUs using Transformers Models.
This Word Does Not Exist
A computer, compiled into the weights of a language model. An exact CPU inside Qwen3.5-4B, with Gated DeltaNet state as RAM.
Extract knowledge from all information sources using gpt and other language models. Index and make Q&A session with information sources.
:sunrise: A comprehensive, cutting-edge open-source framework for next-generation Transformers, with compute-matched benchmarking and a platform for autonomous architecture research.
- auto-research
- benchmark
- deep-learning
- language-models
Run transformers directly on Apple's Neural Engine in Swift bypass coreml entirely
- ane
- apple
- apple-neural-engine
- neural-engine