argonne-lcf / LLM-Inference-BenchLinks
LLM-Inference-Bench
☆50Updated last month
Alternatives and similar repositories for LLM-Inference-Bench
Users that are interested in LLM-Inference-Bench are comparing it to the libraries listed below
Sorting:
- ☆69Updated last year
- LLM Serving Performance Evaluation Harness☆79Updated 6 months ago
- Flash-LLM: Enabling Cost-Effective and Highly-Efficient Large Generative Model Inference with Unstructured Sparsity☆217Updated last year
- ☆74Updated 5 months ago
- [ICLR'25] Fast Inference of MoE Models with CPU-GPU Orchestration☆226Updated 9 months ago
- FlexFlow Serve: Low-Latency, High-Performance LLM Serving☆54Updated last month
- PyTorch library for cost-effective, fast and easy serving of MoE models.☆224Updated last month
- ☆88Updated 9 months ago
- ☆47Updated last year
- Stateful LLM Serving☆81Updated 5 months ago
- ☆81Updated 7 months ago
- PipeInfer: Accelerating LLM Inference using Asynchronous Pipelined Speculation☆30Updated 9 months ago
- Framework to reduce autotune overhead to zero for well known deployments.☆81Updated last week
- ☆38Updated last year
- ☆85Updated 3 years ago
- Fast and memory-efficient exact attention☆91Updated this week
- [DAC'25] Official implement of "HybriMoE: Hybrid CPU-GPU Scheduling and Cache Management for Efficient MoE Inference"☆68Updated 2 months ago
- ☆92Updated 5 months ago
- High-speed GEMV kernels, at most 2.7x speedup compared to pytorch baseline.☆113Updated last year
- PyTorch bindings for CUTLASS grouped GEMM.☆110Updated 3 months ago
- TensorRT LLM Benchmark Configuration☆13Updated last year
- Microsoft Collective Communication Library☆67Updated 9 months ago
- Aims to implement dual-port and multi-qp solutions in deepEP ibrc transport☆61Updated 3 months ago
- kvcached: Elastic KV cache for dynamic GPU sharing and efficient multi-LLM inference.☆66Updated this week
- [OSDI'24] Serving LLM-based Applications Efficiently with Semantic Variable☆180Updated 11 months ago
- TileFusion is an experimental C++ macro kernel template library that elevates the abstraction level in CUDA C for tile processing.☆95Updated 2 months ago
- GPTQ inference TVM kernel☆40Updated last year
- [MLSys'24] Atom: Low-bit Quantization for Efficient and Accurate LLM Serving☆319Updated last year
- A lightweight design for computation-communication overlap.☆160Updated last week
- ☆47Updated 8 months ago