wdlctc / headinferLinks
☆57Updated 4 months ago
Alternatives and similar repositories for headinfer
Users that are interested in headinfer are comparing it to the libraries listed below
Sorting:
- [NeurIP'25 Oral] Query-agnostic KV cache eviction: 3–4× reduction in memory and 2× decrease in latency (Qwen3/2.5, Gemma3, LLaMA3)☆103Updated this week
- A collection of tricks and tools to speed up transformer models☆178Updated 2 weeks ago
- RWKV-7: Surpassing GPT☆95Updated 10 months ago
- Fused Qwen3 MoE layer for faster training, compatible with HF Transformers, LoRA, 4-bit quant, Unsloth☆176Updated this week
- ☆56Updated 3 months ago
- A repository aimed at pruning DeepSeek V3, R1 and R1-zero to a usable size☆68Updated 2 weeks ago
- QuIP quantization☆59Updated last year
- Simple extension on vLLM to help you speed up reasoning model without training.☆189Updated 3 months ago
- Lightweight toolkit package to train and fine-tune 1.58bit Language models☆88Updated 4 months ago
- KV cache compression for high-throughput LLM inference☆138Updated 7 months ago
- Work in progress.☆72Updated 2 months ago
- ☆64Updated 6 months ago
- From GaLore to WeLore: How Low-Rank Weights Non-uniformly Emerge from Low-Rank Gradients. Ajay Jaiswal, Lu Yin, Zhenyu Zhang, Shiwei Liu,…☆48Updated 5 months ago
- [ICLR2025] Breaking Throughput-Latency Trade-off for Long Sequences with Speculative Decoding☆127Updated 9 months ago
- A repository for research on medium sized language models.☆77Updated last year
- ☆150Updated 3 months ago
- Cascade Speculative Drafting☆30Updated last year
- ☆42Updated 4 months ago
- Tree Attention: Topology-aware Decoding for Long-Context Attention on GPU clusters☆129Updated 9 months ago
- Linear Attention Sequence Parallelism (LASP)☆86Updated last year
- CPM.cu is a lightweight, high-performance CUDA implementation for LLMs, optimized for end-device inference and featuring cutting-edge tec…☆192Updated this week
- Fira: Can We Achieve Full-rank Training of LLMs Under Low-rank Constraint?☆115Updated 11 months ago
- Layer-Condensed KV cache w/ 10 times larger batch size, fewer params and less computation. Dramatic speed up with better task performance…☆155Updated 5 months ago
- Self-host LLMs with LMDeploy and BentoML☆22Updated 2 months ago
- ☆54Updated 3 months ago
- ☆86Updated 8 months ago
- Training-free Post-training Efficient Sub-quadratic Complexity Attention. Implemented with OpenAI Triton.☆147Updated last week
- Block Transformer: Global-to-Local Language Modeling for Fast Inference (NeurIPS 2024)☆161Updated 5 months ago
- [EMNLP 2025] The official implementation for paper "Agentic-R1: Distilled Dual-Strategy Reasoning"☆99Updated 3 weeks ago
- Official repository for the paper "NeuZip: Memory-Efficient Training and Inference with Dynamic Compression of Neural Networks". This rep…☆60Updated 10 months ago