stepfun-ai / StepMeshLinks
☆307Updated 3 weeks ago
Alternatives and similar repositories for StepMesh
Users that are interested in StepMesh are comparing it to the libraries listed below
Sorting:
- A lightweight design for computation-communication overlap.☆181Updated last week
- nnScaler: Compiling DNN models for Parallel Training☆118Updated last month
- High performance Transformer implementation in C++.☆135Updated 9 months ago
- Allow torch tensor memory to be released and resumed later☆150Updated this week
- Ultra and Unified CCL☆595Updated this week
- NVSHMEM‑Tutorial: Build a DeepEP‑like GPU Buffer☆138Updated last month
- Pipeline Parallelism Emulation and Visualization☆68Updated 4 months ago
- DeepSeek-V3/R1 inference performance simulator☆170Updated 6 months ago
- ☆124Updated 11 months ago
- Perplexity GPU Kernels☆497Updated last month
- A low-latency & high-throughput serving engine for LLMs☆431Updated last week
- Automated Parallelization System and Infrastructure for Multiple Ecosystems☆80Updated 11 months ago
- Stateful LLM Serving☆86Updated 7 months ago
- Zero Bubble Pipeline Parallelism☆432Updated 5 months ago
- ☆74Updated this week
- ☆90Updated 6 months ago
- [USENIX ATC '24] Accelerating the Training of Large Language Models using Efficient Activation Rematerialization and Optimal Hybrid Paral…☆65Updated last year
- A prefill & decode disaggregated LLM serving framework with shared GPU memory and fine-grained compute isolation.☆112Updated 5 months ago
- Efficient and easy multi-instance LLM serving☆497Updated last month
- MSCCL++: A GPU-driven communication stack for scalable AI applications☆425Updated this week
- ByteCheckpoint: An Unified Checkpointing Library for LFMs☆249Updated 3 months ago
- ☆100Updated last year
- A tiny yet powerful LLM inference system tailored for researching purpose. vLLM-equivalent performance with only 2k lines of code (2% of …☆278Updated 4 months ago
- Since the emergence of chatGPT in 2022, the acceleration of Large Language Model has become increasingly important. Here is a list of pap…☆278Updated 7 months ago
- NVIDIA NVSHMEM is a parallel programming interface for NVIDIA GPUs based on OpenSHMEM. NVSHMEM can significantly reduce multi-process com…☆351Updated last week
- ☆141Updated 9 months ago
- Train speculative decoding models effortlessly and port them smoothly to SGLang serving.☆428Updated last week
- PyTorch library for cost-effective, fast and easy serving of MoE models.☆252Updated last week
- [OSDI'24] Serving LLM-based Applications Efficiently with Semantic Variable☆186Updated last year
- KV cache store for distributed LLM inference☆345Updated last month