63 skills found · Page 1 of 3
xjdr-alt / EntropixEntropy Based Sampling and Parallel CoT Decoding
NVlabs / Fast DLLMOfficial implementation of "Fast-dLLM: Training-free Acceleration of Diffusion LLM by Enabling KV Cache and Parallel Decoding"
opendatalab / MinerU DiffusionA diffusion-based framework for document OCR that replaces autoregressive decoding with block-level parallel diffusion decoding.
TencentARC / VQFRECCV 2022, Oral, VQFR: Blind Face Restoration with Vector-Quantized Dictionary and Parallel Decoder
ttengwang / PDVCEnd-to-End Dense Video Captioning with Parallel Decoding (ICCV 2021)
smart-lty / Nano PEARLDraft-Target Disaggregation LLM Serving System via Parallel Speculative Decoding.
smart-lty / ParallelSpeculativeDecoding[ICLR 2025] PEARL: Parallel Speculative Decoding with Adaptive Draft Length
hao-ai-lab / JacobiForcingJacobi Forcing: Fast and Accurate Diffusion-style Decoding
teelinsan / Parallel DecodingRepository of the paper "Accelerating Transformer Inference for Translation via Parallel Decoding"
mit-han-lab / Lpd[ICLR 2026 Oral] Locality-aware Parallel Decoding for Efficient Autoregressive Image Generation
hp-l33 / ARPG[ICLR 2026] Autoregressive Image Generation with Randomized Parallel Decoding
ZichengXu / Decoding Tree SketchingDecoding Tree Sketching (DTS): a training-free & model agonistic & plug-in framework for LLM parallel reasoning.
IIDA-AILab / PEPSI Fast Image Inpainting With Parallel Decoding NetworkNo description available
raymin0223 / Fast Robust Early ExitFast and Robust Early-Exiting Framework for Autoregressive Language Models with Synchronized Parallel Decoding (EMNLP 2023 Long)
czg1225 / DParallel[ICLR 2026] dParallel: Learnable Parallel Decoding for dLLMs
ML-GSAI / ReFusion[ICLR 2026] Official PyTorch implementation for "ReFusion: A Diffusion Large Language Model with Parallel Autoregressive Decoding"
biren15 / Design And Verification Of LDPC Decoder- Designed the LDPC decoder in the Matlab using the min-sum approach. - Designed quantized RTL in Verilog with the min-sum approach and parallel architecture. - Created modules for all variants of the variable node unit(VNU) and the check-node unit(CNU) based on the H matrix. Created script for module instantiation of VNU and CNU as per the H matrix. - Verified the functionality of the Verilog implementation by self-checking test-bench in Verilog to compare the results with Matlab.
hmarkc / Parallel Prompt DecodingEfficient LLM Inference Acceleration using Prompting
weissenberger / GpuhdMassively Parallel Huffman Decoding on GPUs
furiosa-ai / ParallelBench[ICLR 2026] ParallelBench: Understanding the Tradeoffs of Parallel Decoding in Diffusion LLMs
