☆24Jul 20, 2026Updated 3 months ago
Alternatives and similar repositories for tiny-speculators
Users that are interested in tiny-speculators are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Implemented and benchmarked KV cache compression methods for LLM inference in Triton. Optimized kernels for KIVI and TurboQuant with Flas…☆18Jun 19, 2026Updated 4 months ago
- Plug-and-play PyTorch transformer research framework. Swap attention, FFN, norm, positional, connection, projection, optimizer, scheduler…☆18Oct 25, 2026Updated last week
- ☆13Aug 18, 2026Updated 2 months ago
- pretrain experiments☆14Updated this week
- A reliability harness for running Pi coding agents with local language models.☆23Aug 30, 2026Updated 2 months 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.
- [Preprint] TPPO: Tracking-Value PPO for Language Model Reasoning☆25Oct 10, 2026Updated 3 weeks ago
- Official repo for "Persistent Visual Memory: Sustaining Perception for Deep Generation in LVLMs"☆12May 5, 2026Updated 5 months ago
- ☆17Oct 21, 2025Updated last year
- Speed-of-Light SW efficiency by using ultra low-latency primitives for comms collectives☆13Apr 8, 2026Updated 6 months ago
- LatentLoop: Scaling Looped MoE Models with Asymmetric Compute Allocation☆16Oct 15, 2026Updated 2 weeks ago
- Interactive 3D model of NVIDIA Vera Rubin hardware (superchip, NVL72 compute tray, HGX NVL8) with connection tracing and a guided tour☆16Oct 1, 2026Updated last month
- Homework for STAT 205A - Berkeley☆13Dec 9, 2014Updated 11 years ago
- [ICML 2026] Official implementation for paper: Learning Self-Correction in Vision–Language Models via Rollout Augmentation☆16Jun 4, 2026Updated 4 months ago
- Kiss-gs third-party implementation☆14Aug 31, 2026Updated 2 months ago
- Proton VPN Special Offer - Get 70% off • AdSpecial partner offer. Trusted by over 100 million users worldwide. Tested, Approved and Recommended by Experts.
- ☆14Jun 10, 2025Updated last year
- ☆20Jul 15, 2026Updated 3 months ago
- Resources for RadixMLP☆14Jan 18, 2026Updated 9 months ago
- observability for speculative decoding