stepfun-ai / StepMeshLinks
☆279Updated last week
Alternatives and similar repositories for StepMesh
Users that are interested in StepMesh are comparing it to the libraries listed below
Sorting:
- nnScaler: Compiling DNN models for Parallel Training☆115Updated this week
- A lightweight design for computation-communication overlap.☆155Updated last week
- High performance Transformer implementation in C++.☆129Updated 7 months ago
- Dynamic Memory Management for Serving LLMs without PagedAttention☆407Updated 2 months ago
- ☆113Updated 9 months ago
- Pipeline Parallelism Emulation and Visualization☆60Updated 2 months ago
- DeepSeek-V3/R1 inference performance simulator☆165Updated 4 months ago
- [USENIX ATC '24] Accelerating the Training of Large Language Models using Efficient Activation Rematerialization and Optimal Hybrid Paral…☆61Updated last year
- Train speculative decoding models effortlessly and port them smoothly to SGLang serving.☆313Updated this week
- A low-latency & high-throughput serving engine for LLMs☆405Updated 2 months ago
- Stateful LLM Serving☆81Updated 5 months ago
- Allow torch tensor memory to be released and resumed later☆109Updated last week
- A prefill & decode disaggregated LLM serving framework with shared GPU memory and fine-grained compute isolation.☆104Updated 3 months ago
- ByteCheckpoint: An Unified Checkpointing Library for LFMs☆237Updated last month
- Ultra and Unified CCL☆497Updated this week
- [OSDI'24] Serving LLM-based Applications Efficiently with Semantic Variable☆176Updated 11 months ago
- Perplexity GPU Kernels☆435Updated 2 weeks ago
- Zero Bubble Pipeline Parallelism☆418Updated 3 months ago
- MSCCL++: A GPU-driven communication stack for scalable AI applications☆399Updated this week
- ☆145Updated 5 months ago
- ☆97Updated 11 months ago
- FlexFlow Serve: Low-Latency, High-Performance LLM Serving☆52Updated 3 weeks ago
- Efficient and easy multi-instance LLM serving☆468Updated this week
- Automated Parallelization System and Infrastructure for Multiple Ecosystems☆79Updated 9 months ago
- KV cache store for distributed LLM inference☆311Updated 2 months ago
- Chimera: bidirectional pipeline parallelism for efficiently training large-scale models.☆66Updated 5 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…☆266Updated 5 months ago
- A tiny yet powerful LLM inference system tailored for researching purpose. vLLM-equivalent performance with only 2k lines of code (2% of …☆240Updated 2 months ago
- ☆68Updated last year
- ☆43Updated last year