simon-mo / vLLM-Benchmark
☆16Updated last week
Alternatives and similar repositories for vLLM-Benchmark:
Users that are interested in vLLM-Benchmark are comparing it to the libraries listed below
- Stateful LLM Serving☆63Updated last month
- extensible collectives library in triton☆85Updated 3 weeks ago
- ☆45Updated 9 months ago
- Perplexity GPU Kernels☆251Updated this week
- DeeperGEMM: crazy optimized version☆67Updated 3 weeks ago
- ☆78Updated 5 months ago
- ☆34Updated 3 months ago
- ☆68Updated last month
- Microsoft Collective Communication Library☆65Updated 5 months ago
- Example of applying CUDA graphs to LLaMA-v2☆12Updated last year
- ☆103Updated 8 months ago
- A minimal implementation of vllm.☆39Updated 8 months ago
- ☆53Updated 7 months ago
- Fairring (FAIR + Herring) is a plug-in for PyTorch that provides a process group for distributed training that outperforms NCCL at large …☆65Updated 3 years ago
- LLM Serving Performance Evaluation Harness☆77Updated 2 months ago
- Ultra | Ultimate | Unified CCL☆59Updated 2 months ago
- ☆72Updated 3 years ago
- ☆68Updated 3 months ago
- PyTorch bindings for CUTLASS grouped GEMM.☆81Updated 5 months ago
- A resilient distributed training framework☆94Updated last year
- Automated Parallelization System and Infrastructure for Multiple Ecosystems☆78Updated 5 months ago
- ☆117Updated last year
- (NeurIPS 2022) Automatically finding good model-parallel strategies, especially for complex models and clusters.☆38Updated 2 years ago
- [ICLR2025] Breaking Throughput-Latency Trade-off for Long Sequences with Speculative Decoding☆115Updated 4 months ago
- ☆59Updated 10 months ago
- ☆31Updated last week
- ☆82Updated last month
- FlexFlow Serve: Low-Latency, High-Performance LLM Serving☆34Updated last week
- ☆55Updated 2 weeks ago
- PyTorch distributed training acceleration framework☆48Updated 2 months ago