☆156Mar 4, 2025Updated last year
Alternatives and similar repositories for deepseekv2-profile
Users that are interested in deepseekv2-profile are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- High performance RMSNorm Implement by using SM Core Storage(Registers and Shared Memory)☆30Jan 22, 2026Updated 6 months ago
- ☆37Aug 7, 2025Updated last year
- ☆271Jul 11, 2024Updated 2 years ago
- ☆122May 16, 2025Updated last year
- FP16xINT4 LLM inference kernel that can achieve near-ideal ~4x speedups up to medium batchsizes of 16-32 tokens.☆1,128Sep 4, 2024Updated last year
- Managed hosting for WordPress and PHP on Cloudways • AdManaged hosting for WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Deploy in minutes on Cloudways by DigitalOcean.
- Compare different hardware platforms via the Roofline Model for LLM inference tasks.☆125Mar 13, 2024Updated 2 years ago
- 使用 cutlass 仓库在 ada 架构上实现 fp8 的 flash attention☆82Aug 12, 2024Updated 2 years ago
- ☆23Aug 14, 2024Updated 2 years ago
- ☆65Apr 26, 2025Updated last year
- flash attention tutorial written in python, triton, cuda, cutlass☆532Jan 20, 2026Updated 6 months ago
- A lightweight design for computation-communication overlap.☆244Jan 20, 2026Updated 6 months ago
- ☆13Jan 7, 2025Updated last year
- Dynamic Memory Management for Serving LLMs without PagedAttention☆512Jul 17, 2026Updated 3 weeks ago
- Implement Flash Attention using Cute.☆111Dec 17, 2024Updated last year
- Wordpress hosting with auto-scaling - Free Trial Offer • AdFully Managed hosting for WordPress and WooCommerce businesses that need reliable, auto-scalable performance. Cloudways SafeUpdates now available.
- DeeperGEMM: crazy optimized version☆86May 5, 2025Updated last year
- Standalone Flash Attention v2 kernel without libtorch dependency☆113Sep 10, 2024Updated last year
- Hydragen: High-Throughput LLM Inference with Shared Prefixes☆57May 10, 2024Updated 2 years ago
- 使用 cutlass 实现 flash-attention 精简版，具有教学意义☆59Aug 12, 2024Updated 2 years ago
- A fast communication-overlapping library for tensor/expert parallelism on GPUs.☆1,353Aug 28, 2025Updated 11 months ago
- ☆54May 19, 2025Updated last year
- Tile-based language built for AI computation across all scales☆185Updated this week
- Perplexity GPU Kernels☆600Nov 7, 2025Updated 9 months ago
- Fast inference from large lauguage models via speculative decoding☆924Aug 22, 2024Updated last year
- Deploy open-source AI quickly and easily - Special Bonus Offer • AdRunpod Hub is built for open source. One-click deployment and autoscaling endpoints without provisioning your own infrastructure.
- Allow torch tensor memory to be released and resumed later☆267Updated this week
- QQQ is an innovative and hardware-optimized W4A8 quantization solution for LLMs.☆160Aug 21, 2025Updated 11 months ago
- 🐳 Efficient Triton implementations for "Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse Attention"☆1,018Feb 5, 2026Updated 6 months ago
- Benchmark tests supporting the TiledCUDA library.☆19Nov 19, 2024Updated last year
- Terminal UI for NVIDIA Nsight Systems profiles — timeline viewer, kernel navigator, NVTX hierarchy☆73Updated this week
- Materials for learning SGLang☆871Jan 5, 2026Updated 7 months ago
- Distributed Compiler based on Triton for Parallel Systems☆1,518Updated this week
- [ICLR 2025] DuoAttention: Efficient Long-Context LLM Inference with Retrieval and Streaming Heads☆540Feb 10, 2025Updated last year
- ☆118May 31, 2025Updated last year
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- USP: Unified (a.k.a. Hybrid, 2D) Sequence Parallel Attention for Long Context Transformers Model Training and Inference☆686May 21, 2026Updated 2 months ago
- Distributed MoE in a Single Kernel [NeurIPS '25]☆281May 5, 2026Updated 3 months ago
- DeepSeek-V3/R1 inference performance simulator☆194Mar 27, 2025Updated last year
- [ICLR 2025] PEARL: Parallel Speculative Decoding with Adaptive Draft Length☆171Dec 23, 2025Updated 7 months ago
- Odysseus: Playground of LLM Sequence Parallelism☆83Jun 17, 2024Updated 2 years ago
- how to optimize some algorithm in cuda.☆3,199Updated this week
- An efficient implementation of the NSA (Native Sparse Attention) kernel☆134Jun 24, 2025Updated last year