efeslab / fiddlerLinks
[ICLR'25] Fast Inference of MoE Models with CPU-GPU Orchestration
☆249Updated last year
Alternatives and similar repositories for fiddler
Users that are interested in fiddler are comparing it to the libraries listed below
Sorting:
- [NeurIPS 2024] KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization☆395Updated last year
- [MLSys'24] Atom: Low-bit Quantization for Efficient and Accurate LLM Serving☆331Updated last year
- [ICLR2025] Breaking Throughput-Latency Trade-off for Long Sequences with Speculative Decoding☆135Updated last year
- PyTorch library for cost-effective, fast and easy serving of MoE models.☆265Updated 2 months ago
- GEAR: An Efficient KV Cache Compression Recipefor Near-Lossless Generative Inference of LLM☆172Updated last year
- [ICML 2024] KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache☆343Updated last month
- Flash-LLM: Enabling Cost-Effective and Highly-Efficient Large Generative Model Inference with Unstructured Sparsity☆230Updated 2 years ago
- 16-fold memory access reduction with nearly no loss☆109Updated 8 months ago
- Boosting 4-bit inference kernels with 2:4 Sparsity☆89Updated last year
- An efficient GPU support for LLM inference with x-bit quantization (e.g. FP6,FP5).☆276Updated 5 months ago
- [ICML 2024] Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inference☆360Updated 5 months ago
- ☆156Updated 10 months ago
- ☆348Updated last year
- KV cache compression for high-throughput LLM inference☆148Updated 10 months ago
- QUICK: Quantization-aware Interleaving and Conflict-free Kernel for efficient LLM inference☆118Updated last year
- PyTorch bindings for CUTLASS grouped GEMM.☆135Updated 6 months ago
- Applied AI experiments and examples for PyTorch☆311Updated 4 months ago
- [ICLR 2025] Palu: Compressing KV-Cache with Low-Rank Projection☆149Updated 10 months ago
- A safetensors extension to efficiently store sparse quantized tensors on disk☆220Updated last week
- Accelerating MoE with IO and Tile-aware Optimizations☆351Updated last week
- [ICLR2025 Spotlight] MagicPIG: LSH Sampling for Efficient LLM Generation☆244Updated last year
- Efficient LLM Inference over Long Sequences☆394Updated 5 months ago
- Fast low-bit matmul kernels in Triton☆410Updated this week
- Collection of kernels written in Triton language☆173Updated 8 months ago
- ☆296Updated 5 months ago
- scalable and robust tree-based speculative decoding algorithm☆365Updated 10 months ago
- Autonomous GPU Kernel Generation via Deep Agents☆187Updated last week
- ☆115Updated last year
- a minimal cache manager for PagedAttention, on top of llama3.☆127Updated last year
- Dynamic Memory Management for Serving LLMs without PagedAttention☆448Updated 6 months ago