facebookresearch / fastgenLinks
Simple high-throughput inference library
☆127Updated 3 months ago
Alternatives and similar repositories for fastgen
Users that are interested in fastgen are comparing it to the libraries listed below
Sorting:
- Lightweight toolkit package to train and fine-tune 1.58bit Language models☆83Updated 3 months ago
- RWKV-7: Surpassing GPT☆94Updated 9 months ago
- Samples of good AI generated CUDA kernels☆89Updated 2 months ago
- Inference of Mamba models in pure C☆190Updated last year
- Tree Attention: Topology-aware Decoding for Long-Context Attention on GPU clusters☆129Updated 8 months ago
- Storing long contexts in tiny caches with self-study☆140Updated this week
- Simple and efficient DeepSeek V3 SFT using pipeline parallel and expert parallel, with both FP8 and BF16 trainings☆76Updated last month
- PyTorch implementation of models from the Zamba2 series.☆184Updated 7 months ago
- 👷 Build compute kernels☆106Updated last week
- Training-free Post-training Efficient Sub-quadratic Complexity Attention. Implemented with OpenAI Triton.☆145Updated this week
- Optimizing Causal LMs through GRPO with weighted reward functions and automated hyperparameter tuning using Optuna☆55Updated 6 months ago
- NanoGPT-speedrunning for the poor T4 enjoyers☆69Updated 4 months ago
- an open source reproduction of NVIDIA's nGPT (Normalized Transformer with Representation Learning on the Hypersphere)☆105Updated 5 months ago
- NanoGPT (124M) quality in 2.67B tokens☆28Updated 2 weeks ago
- Memory optimized Mixture of Experts☆54Updated last month
- ☆18Updated last year
- Fused Qwen3 MoE layer for faster training, compatible with HF Transformers, LoRA, 4-bit quant, Unsloth☆167Updated this week
- Official repository for the paper "NeuZip: Memory-Efficient Training and Inference with Dynamic Compression of Neural Networks". This rep…☆59Updated 9 months ago
- Make triton easier☆47Updated last year
- Experiments on speculative sampling with Llama models☆128Updated 2 years ago
- Pivotal Token Search☆121Updated last month
- ☆51Updated last year
- ☆59Updated last month
- Python bindings for ggml☆146Updated 11 months ago
- ☆60Updated 7 months ago
- ☆38Updated last year
- A minimalistic C++ Jinja templating engine for LLM chat templates☆170Updated 2 weeks ago
- DeMo: Decoupled Momentum Optimization☆190Updated 8 months ago
- Repo for "LoLCATs: On Low-Rank Linearizing of Large Language Models"☆245Updated 6 months ago
- ☆49Updated last year