sgl-project / sgl-kernel-npuLinks
SGLang kernel library for NPU
☆81Updated this week
Alternatives and similar repositories for sgl-kernel-npu
Users that are interested in sgl-kernel-npu are comparing it to the libraries listed below
Sorting:
- ☆153Updated 9 months ago
- Train speculative decoding models effortlessly and port them smoothly to SGLang serving.☆539Updated this week
- LLM training technologies developed by kwai☆66Updated 2 weeks ago
- Ascend TileLang adapter☆161Updated this week
- Compare different hardware platforms via the Roofline Model for LLM inference tasks.☆119Updated last year
- ☆328Updated last month
- A prefill & decode disaggregated LLM serving framework with shared GPU memory and fine-grained compute isolation.☆118Updated 6 months ago
- DeepSeek-V3/R1 inference performance simulator☆169Updated 8 months ago
- ☆102Updated last year
- Summary of the Specs of Commonly Used GPUs for Training and Inference of LLM☆67Updated 4 months ago
- Allow torch tensor memory to be released and resumed later☆184Updated last week
- ☆134Updated last week
- PyTorch distributed training acceleration framework☆53Updated 4 months ago
- A lightweight design for computation-communication overlap.☆194Updated 2 months ago
- ☆130Updated 11 months ago
- High performance Transformer implementation in C++.☆143Updated 10 months ago
- Triton adapter for Ascend. Mirror of https://gitee.com/ascend/triton-ascend☆88Updated last week
- ☆75Updated last year
- Utility scripts for PyTorch (e.g. Make Perfetto show some disappearing kernels, Memory profiler that understands more low-level allocatio…☆72Updated 3 months ago
- ☆97Updated 8 months ago
- Materials for learning SGLang☆682Updated last week
- FlagScale is a large model toolkit based on open-sourced projects.☆421Updated last week
- A tiny yet powerful LLM inference system tailored for researching purpose. vLLM-equivalent performance with only 2k lines of code (2% of …☆294Updated 6 months ago
- ☆112Updated 6 months ago
- DLSlime: Flexible & Efficient Heterogeneous Transfer Toolkit☆82Updated this week
- Efficient and easy multi-instance LLM serving☆517Updated 3 months ago
- ☆515Updated 3 weeks ago
- 注释的nano_vllm仓库,并且完成了MiniCPM4的适配以及注册新模型的功能☆114Updated 4 months ago
- Fast and memory-efficient exact attention☆104Updated this week
- ☆44Updated last year