yandex-research / specexec
☆40Updated this week
Related projects ⓘ
Alternatives and complementary repositories for specexec
- Fast Inference of MoE Models with CPU-GPU Orchestration☆170Updated last week
- ring-attention experiments☆95Updated 3 weeks ago
- Official implementation of the paper "Linear Transformers with Learnable Kernel Functions are Better In-Context Models"☆156Updated 8 months ago
- Token Omission Via Attention☆119Updated 3 weeks ago
- Tree Attention: Topology-aware Decoding for Long-Context Attention on GPU clusters☆104Updated last month
- Fast Matrix Multiplications for Lookup Table-Quantized LLMs☆183Updated last month
- The source code of our work "Prepacking: A Simple Method for Fast Prefilling and Increased Throughput in Large Language Models"☆56Updated 3 weeks ago
- Breaking Throughput-Latency Trade-off for Long Sequences with Speculative Decoding☆70Updated this week
- QuIP quantization☆46Updated 7 months ago
- A safetensors extension to efficiently store sparse quantized tensors on disk☆46Updated this week
- ☆182Updated 3 weeks ago
- Simple and fast low-bit matmul kernels in CUDA / Triton☆133Updated this week
- Triton-based implementation of Sparse Mixture of Experts.☆184Updated 3 weeks ago
- ☆60Updated last week
- ☆36Updated 4 months ago
- Official code for "SWARM Parallelism: Training Large Models Can Be Surprisingly Communication-Efficient"☆127Updated 10 months ago
- The official repo for "LLoCo: Learning Long Contexts Offline"☆110Updated 4 months ago
- GEAR: An Efficient KV Cache Compression Recipefor Near-Lossless Generative Inference of LLM☆146Updated 3 months ago
- Code for the paper "QMoE: Practical Sub-1-Bit Compression of Trillion-Parameter Models".☆261Updated last year
- ☆183Updated 6 months ago
- PyTorch half precision gemm lib w/ fused optional bias + optional relu/gelu☆38Updated 2 months ago
- Layer-Condensed KV cache w/ 10 times larger batch size, fewer params and less computation. Dramatic speed up with better task performance…☆137Updated this week
- PB-LLM: Partially Binarized Large Language Models☆146Updated 11 months ago
- ShiftAddLLM: Accelerating Pretrained LLMs via Post-Training Multiplication-Less Reparameterization☆85Updated 3 weeks ago
- An efficent implementation of the method proposed in "The Era of 1-bit LLMs"☆154Updated 3 weeks ago
- 🚀 Efficiently (pre)training foundation models with native PyTorch features, including FSDP for training and SDPA implementation of Flash…☆190Updated 2 weeks ago
- A toolkit for fine-tuning, inferencing, and evaluating GreenBitAI's LLMs.☆72Updated 3 weeks ago
- ☆24Updated last year