fw-ai / llama-cuda-graph-exampleLinks
Example of applying CUDA graphs to LLaMA-v2
☆12Updated last year
Alternatives and similar repositories for llama-cuda-graph-example
Users that are interested in llama-cuda-graph-example are comparing it to the libraries listed below
Sorting:
- ☆74Updated 3 months ago
- Boosting 4-bit inference kernels with 2:4 Sparsity☆80Updated 10 months ago
- Hydragen: High-Throughput LLM Inference with Shared Prefixes☆40Updated last year
- ring-attention experiments☆143Updated 9 months ago
- ☆26Updated last year
- [ICLR2025] Breaking Throughput-Latency Trade-off for Long Sequences with Speculative Decoding☆121Updated 7 months ago
- extensible collectives library in triton☆87Updated 3 months ago
- ☆49Updated last month
- A safetensors extension to efficiently store sparse quantized tensors on disk☆135Updated this week
- QuIP quantization☆54Updated last year
- Framework to reduce autotune overhead to zero for well known deployments.☆79Updated last week
- GEAR: An Efficient KV Cache Compression Recipefor Near-Lossless Generative Inference of LLM☆165Updated last year
- ☆106Updated 10 months ago
- ☆71Updated 2 weeks ago
- ☆60Updated 2 months ago
- [ICLR'25] Fast Inference of MoE Models with CPU-GPU Orchestration☆218Updated 7 months ago
- vLLM performance dashboard☆32Updated last year
- Code for data-aware compression of DeepSeek models☆36Updated last month
- ☆83Updated 8 months ago
- Repository for Sparse Finetuning of LLMs via modified version of the MosaicML llmfoundry☆42Updated last year
- A minimal implementation of vllm.☆49Updated 11 months ago
- DeeperGEMM: crazy optimized version☆69Updated 2 months ago
- The source code of our work "Prepacking: A Simple Method for Fast Prefilling and Increased Throughput in Large Language Models" [AISTATS …☆59Updated 9 months ago
- Triton-based implementation of Sparse Mixture of Experts.☆225Updated 7 months ago
- Accelerate LLM preference tuning via prefix sharing with a single line of code☆42Updated last week
- A Suite for Parallel Inference of Diffusion Transformers (DiTs) on multi-GPU Clusters☆47Updated 11 months ago
- Best practices for testing advanced Mixtral, DeepSeek, and Qwen series MoE models using Megatron Core MoE.☆32Updated this week
- Docker image NVIDIA GH200 machines - optimized for vllm serving and hf trainer finetuning☆46Updated 4 months ago
- Collection of kernels written in Triton language☆136Updated 3 months ago
- Odysseus: Playground of LLM Sequence Parallelism☆70Updated last year