yandex-research / specexec
☆42Updated 2 weeks ago
Related projects ⓘ
Alternatives and complementary repositories for specexec
- Fast Inference of MoE Models with CPU-GPU Orchestration☆172Updated this week
- ring-attention experiments☆97Updated last month
- GEAR: An Efficient KV Cache Compression Recipefor Near-Lossless Generative Inference of LLM☆147Updated 4 months ago
- Fast Matrix Multiplications for Lookup Table-Quantized LLMs☆187Updated this week
- ☆69Updated this week
- Breaking Throughput-Latency Trade-off for Long Sequences with Speculative Decoding☆79Updated this week
- Code for Palu: Compressing KV-Cache with Low-Rank Projection☆57Updated this week
- Triton-based implementation of Sparse Mixture of Experts.☆185Updated last month
- Simple and fast low-bit matmul kernels in CUDA / Triton☆145Updated last week
- The source code of our work "Prepacking: A Simple Method for Fast Prefilling and Increased Throughput in Large Language Models"☆56Updated last month
- LLM KV cache compression made easy☆168Updated this week
- A safetensors extension to efficiently store sparse quantized tensors on disk☆51Updated this week
- ☆189Updated 6 months ago
- Boosting 4-bit inference kernels with 2:4 Sparsity☆51Updated 2 months ago
- ☆96Updated last month
- [ICML 2024] KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache☆241Updated last month
- QuIP quantization☆46Updated 8 months ago
- Token Omission Via Attention☆121Updated last month
- ☆38Updated 4 months ago
- Tree Attention: Topology-aware Decoding for Long-Context Attention on GPU clusters☆104Updated last month
- Explorations into some recent techniques surrounding speculative decoding☆212Updated last year
- [ICML 2024] Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inference☆203Updated 3 weeks ago
- REST: Retrieval-Based Speculative Decoding, NAACL 2024☆176Updated this week
- PB-LLM: Partially Binarized Large Language Models☆148Updated last year
- ShiftAddLLM: Accelerating Pretrained LLMs via Post-Training Multiplication-Less Reparameterization☆87Updated last month
- 🚀 Efficiently (pre)training foundation models with native PyTorch features, including FSDP for training and SDPA implementation of Flash…☆194Updated this week
- ☆101Updated last month
- [NeurIPS 2024] KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization☆305Updated 3 months ago
- Layer-Condensed KV cache w/ 10 times larger batch size, fewer params and less computation. Dramatic speed up with better task performance…☆139Updated this week