efeslab / fiddlerLinks
[ICLR'25] Fast Inference of MoE Models with CPU-GPU Orchestration
☆234Updated 10 months ago
Alternatives and similar repositories for fiddler
Users that are interested in fiddler are comparing it to the libraries listed below
Sorting:
- [MLSys'24] Atom: Low-bit Quantization for Efficient and Accurate LLM Serving☆320Updated last year
- [NeurIPS 2024] KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization☆383Updated last year
- PyTorch library for cost-effective, fast and easy serving of MoE models.☆241Updated 2 months ago
- [ICLR2025] Breaking Throughput-Latency Trade-off for Long Sequences with Speculative Decoding☆128Updated 10 months ago
- Flash-LLM: Enabling Cost-Effective and Highly-Efficient Large Generative Model Inference with Unstructured Sparsity☆221Updated 2 years ago
- [ICML 2024] KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache☆326Updated last week
- GEAR: An Efficient KV Cache Compression Recipefor Near-Lossless Generative Inference of LLM☆168Updated last year
- Boosting 4-bit inference kernels with 2:4 Sparsity☆82Updated last year
- An efficient GPU support for LLM inference with x-bit quantization (e.g. FP6,FP5).☆265Updated 2 months ago
- [ICML 2024] Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inference☆339Updated 2 months ago
- ☆142Updated 7 months ago
- 16-fold memory access reduction with nearly no loss☆105Updated 6 months ago
- A safetensors extension to efficiently store sparse quantized tensors on disk☆164Updated this week
- ☆338Updated last year
- [ICLR 2025] Palu: Compressing KV-Cache with Low-Rank Projection☆140Updated 7 months ago
- KV cache compression for high-throughput LLM inference☆141Updated 7 months ago
- [ICLR2025 Spotlight] MagicPIG: LSH Sampling for Efficient LLM Generation☆238Updated 9 months ago
- ☆112Updated last year
- Fast low-bit matmul kernels in Triton☆373Updated last week
- [ICML 2024] BiLLM: Pushing the Limit of Post-Training Quantization for LLMs☆225Updated 8 months ago
- PyTorch bindings for CUTLASS grouped GEMM.☆123Updated 4 months ago
- ☆280Updated 2 months ago
- QUICK: Quantization-aware Interleaving and Conflict-free Kernel for efficient LLM inference☆118Updated last year
- Collection of kernels written in Triton language☆155Updated 5 months ago
- a minimal cache manager for PagedAttention, on top of llama3.☆122Updated last year
- Code for data-aware compression of DeepSeek models☆54Updated 3 months ago
- scalable and robust tree-based speculative decoding algorithm☆359Updated 8 months ago
- LLM Serving Performance Evaluation Harness☆79Updated 7 months ago
- Dynamic Memory Management for Serving LLMs without PagedAttention☆421Updated 4 months ago
- The official implementation of the EMNLP 2023 paper LLM-FP4☆215Updated last year