DeepLink-org / dlinferLinks
☆49Updated this week
Alternatives and similar repositories for dlinfer
Users that are interested in dlinfer are comparing it to the libraries listed below
Sorting:
- DashInfer is a native LLM inference engine aiming to deliver industry-leading performance atop various hardware architectures, including …☆253Updated this week
- FlagScale is a large model toolkit based on open-sourced projects.☆280Updated this week
- ☆127Updated 5 months ago
- ☆138Updated last year
- Transformer related optimization, including BERT, GPT☆39Updated 2 years ago
- InternEvo is an open-sourced lightweight training framework aims to support model pre-training without the need for extensive dependencie…☆389Updated this week
- ☆79Updated last year
- Built upon Megatron-Deepspeed and HuggingFace Trainer, EasyLLM has reorganized the code logic with a focus on usability. While enhancing …☆46Updated 8 months ago
- An industrial extension library of pytorch to accelerate large scale model training☆36Updated last month
- ☆166Updated this week
- ☆137Updated 2 months ago
- Simple Dynamic Batching Inference☆145Updated 3 years ago
- PyTorch bindings for CUTLASS grouped GEMM.☆122Updated 5 months ago
- QQQ is an innovative and hardware-optimized W4A8 quantization solution for LLMs.☆124Updated last month
- ☆193Updated 3 weeks ago
- ☆332Updated 4 months ago
- A flexible and efficient training framework for large-scale alignment tasks☆364Updated this week
- PyTorch distributed training acceleration framework☆49Updated 3 months ago
- Triton Documentation in Chinese Simplified / Triton 中文文档☆71Updated last month
- ☆44Updated 7 months ago
- ☆58Updated 6 months ago
- A collection of memory efficient attention operators implemented in the Triton language.☆271Updated 11 months ago
- A prefill & decode disaggregated LLM serving framework with shared GPU memory and fine-grained compute isolation.☆80Updated 2 weeks ago
- 📚FFPA(Split-D): Extend FlashAttention with Split-D for large headdim, O(1) GPU SRAM complexity, 1.8x~3x↑🎉 faster than SDPA EA.☆183Updated 3 weeks ago
- USP: Unified (a.k.a. Hybrid, 2D) Sequence Parallel Attention for Long Context Transformers Model Training and Inference☆506Updated last week
- Transformer related optimization, including BERT, GPT☆17Updated last year
- ☆85Updated 2 months ago
- Compare different hardware platforms via the Roofline Model for LLM inference tasks.☆100Updated last year
- Ascend PyTorch adapter (torch_npu). Mirror of https://gitee.com/ascend/pytorch☆369Updated this week
- ☆67Updated 7 months ago