☆22Apr 17, 2025Updated last year
Alternatives and similar repositories for dkernel
Users that are interested in dkernel are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Cold Compress is a hackable, lightweight, and open-source toolkit for creating and benchmarking cache compression methods built on top of…☆153Aug 9, 2024Updated 2 years ago
- ☆18Sep 23, 2025Updated 10 months ago
- Using FlexAttention to compute attention with different masking patterns☆47Sep 22, 2024Updated last year
- KV cache compression for high-throughput LLM inference☆159Feb 5, 2025Updated last year
- Beyond KV Caching: Shared Attention for Efficient LLMs☆20Jul 19, 2024Updated 2 years ago
- GPUs on demand by Runpod - Special Offer Available • AdRun AI, ML, and HPC workloads on powerful cloud GPUs—without limits or wasted spend. Deploy GPUs in under a minute and pay by the second.
- Boosting 4-bit inference kernels with 2:4 Sparsity☆100Sep 4, 2024Updated last year
- A variant of Ahash written in C++.☆10Mar 20, 2023Updated 3 years ago
- To mitigate position bias in LLMs, especially in long-context scenarios, we scale only one dimension of LLMs, reducing position bias and …☆12Jun 18, 2024Updated 2 years ago
- ☆13Aug 13, 2024Updated last year
- Official implementation of Vector-ICL: In-context Learning with Continuous Vector Representations (ICLR 2025)☆24Jun 2, 2025Updated last year
- lime-ner: extending LIME for Named Entity Recognition☆10Aug 15, 2018Updated 7 years ago
- A transfer learning-based random forest regression model☆15Aug 25, 2018Updated 7 years ago
- Code for "Fine-Tuning by Curriculum Learning for Non-Autoregressive Neural Machine Translation"☆13Jul 10, 2020Updated 6 years ago
- Java-like Language with Static Information Flow Types☆14May 5, 2025Updated last year
- GPUs on demand by Runpod - Special Offer Available • AdRun AI, ML, and HPC workloads on powerful cloud GPUs—without limits or wasted spend. Deploy GPUs in under a minute and pay by the second.
- Released code for the paper: Where To Look: Focus Regions for Visual Question Answering. (CVPR2016)☆10Apr 8, 2020Updated 6 years ago
- Vocabulary Parallelism☆26Mar 10, 2025Updated last year
- ☆15Mar 20, 2025Updated last year
- [ACL 2024 Findings] Light-PEFT: Lightening Parameter-Efficient Fine-Tuning via Early Pruning☆13Sep 2, 2024Updated last year
- [CVPR 2025 Workshop] PAINT (Paying Attention to INformed Tokens) is a plug-and-play framework that intervenes in the self-attention of th…☆20Jul 19, 2026Updated 3 weeks ago
- Contrast Subgraph Mining from Coherent Cores☆13Feb 20, 2018Updated 8 years ago
- ☆16Dec 21, 2023Updated 2 years ago
- FocusLLM: Scaling LLM’s Context by Parallel Decoding☆45Dec 8, 2024Updated last year
- ☆11Jan 12, 2021Updated 5 years ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- An LLM inference engine, written in C++☆20Mar 30, 2026Updated 4 months ago
- Code of the paper "SPINE: Structural Identity Preserved Inductive Network Embedding"☆12Jul 29, 2019Updated 7 years ago
- Sparse Backpropagation for Mixture-of-Expert Training☆30Jul 2, 2024Updated 2 years ago
- ☆13Aug 23, 2017Updated 8 years ago
- An adaptive training algorithm for residual network☆17Aug 22, 2020Updated 5 years ago
- ☆12Dec 7, 2018Updated 7 years ago
- A model serving framework for various research and production scenarios. Seamlessly built upon the PyTorch and HuggingFace ecosystem.☆23Oct 11, 2024Updated last year
- ☆63May 19, 2025Updated last year
- ☆16Oct 20, 2021Updated 4 years ago
- Serverless GPU API endpoints on Runpod - Get Bonus Credits • AdSkip the infrastructure headaches. Auto-scaling, pay-as-you-go, no-ops approach lets you focus on innovating your application.
- Quantized Attention on GPU☆45Nov 22, 2024Updated last year
- Accelerated Confergence for Counterfactual Learning to Rank☆17Jan 21, 2022Updated 4 years ago
- ☆328Jul 10, 2025Updated last year
- ☆21May 30, 2025Updated last year
- [ICLR2025] Breaking Throughput-Latency Trade-off for Long Sequences with Speculative Decoding☆156Dec 4, 2024Updated last year
- The official repo for the paper "Optimizing LLM Inference Throughput via Memory-aware and SLA-constrained Dynamic Batching"☆18Mar 17, 2025Updated last year
- A Pytorch implementation of the KWNG estimator☆14Jul 25, 2024Updated 2 years ago