GeezerVisonThe World Wide Web, restored to 800 pixels of glory. |
| Home|About|Gaming cabinet|Archives|How it works|Starter sites |
GeezerVison is showing github.com — Build software better, together
#
parallel-decodingHere are 25 public repositories matching this topic...Language: All
Filter by language
Sort: Most stars
Sort options
[EMNLP 2026] 📚 A curated list of Awesome Efficient dLLMs Papers with Codes
diffusion model-compression multimodal system-framework inference-acceleration kv-cache efficient-deep-learning parallel-decoding training-efficiency diffusion-language-models multimodal-diffusion-language-models
[NeurIPS 2026] DMax: Aggressive Parallel Decoding for dLLMs
acceleration efficiency large-language-models parallel-decoding diffusion-language-models multi-token-prediction
[ICML 2026] When Drafts Evolve: Speculative Decoding Meets Online Learning
online-learning efficient-inference large-language-models llm speculative-decoding parallel-decoding on-policy-distillation
Repository of the paper "Accelerating Transformer Inference for Translation via Parallel Decoding"
natural-language-processing deep-learning neural-network transformers jacobi-iteration decoding-algorithm parallel-decoding jacobi-decoding
A 4B diffusion grounding model for fast, precise visual evidence extraction. Unifies diverse grounding tasks through parallel decoding, with optional self-speculative decoding delivering 4.51x autoregressive throughput on COCO.
ocr object-detection pointing diffusion-model visual-grounding vision-language-model speculative-decoding parallel-decoding gui-grounding diffusion-language-model
[ICML 2026] Jacobi Forcing: Fast and Accurate Diffusion-style Decoding
[ICLR 2026 Oral] Locality-aware Parallel Decoding for Efficient Autoregressive Image Generation
[ICLR 2026] Autoregressive Image Generation with Randomized Parallel Decoding
JEV-inspired parallel decisions for CUDA LLMs. One context, many decisions. vLLM API, game-agent examples, and reproducible benchmarks.
[ICLR 2026] dParallel: Learnable Parallel Decoding for dLLMs
acceleration efficiency distillation large-language-models parallel-decoding diffusion-language-models few-step
[ICLR 2026] ParallelBench: Understanding the Tradeoffs of Parallel Decoding in Diffusion LLMs
Implementation of Flash-DLM (paper: FlashDLM: Accelerating Diffusion Language Models via Efficient KV Caching and Guided Diffusion). Provides training-free methods to accelerate diffusion language model inference.
acceleration efficient-inference diffusion-models kv-cache efficient-deep-learning large-language-models parallel-decoding diffusion-langauge-model diffusion-large-language-model
Parallel Decoding of Language Models: A Survey. A systematic survey of parallel decoding, covering speculative decoding, diffusion LLMs, etc...
efficient-inference large-language-models speculative-decoding parallel-decoding efficient-reasoning
This repository contains the source code for COrAL, an Order-Agnostic Language Modeling framework for Efficient Iterative Refinement.
Run Next-Concept Modeling (NCM) on the Apple Silicon GPU with MLX: HazyResearch's released checkpoints with verified parity to PyTorch, plus from-scratch training and benchmarks.
python metal cuda text-generation language-modeling sudoku ncm mlx vector-quantization machine-learning-research non-autoregressive coarse-to-fine apple-silicon residual-vector-quantization tinystories parallel-decoding diffusion-language-model next-concept-modeling
Predictive-State Flows (PSF): a flow prior generates K predictive states, each summarizing only the preceding blocks; a block decoder writes all blocks in parallel. Code and checkpoints for arXiv 2610.12898.
text-generation language-modeling pytorch generative-models diffusion-models non-autoregressive rectified-flow flow-matching parallel-decoding diffusion-language-model
Strata 125B MoE + JEV mode: llama.cpp fork with parallel-decision endpoints (yes/no in ~10ms), an MCP server, and a llama-swap router swarm for Claude Code & DeepSeek Harness.
Diffusion VLM papers indexed with one feature schema, plus decode-behaviour traces measured through a single instrumentation path
Educational implementation and visualization of autoregressive, DFlash-inspired, and DFlash2-inspired LLM decoding with a tiny Transformer benchmark.
docker benchmark transformers slm language-model inference-optimization cpu-inference llm-inference speculative-decoding parallel-decoding small-language-models block-diffusion dflash dflash2
What parallel commitment costs a masked diffusion LM: a 4-page note, measured on a task with a decidable verifier. Produced by the Rust stack (candle-mi -> canvas).
rust language-models strips reproducibility ai-planning candle blocksworld mechanistic-interpretability discrete-diffusion parallel-decoding mdlm masked-diffusion diffusion-language-models any-order-decoding planbench
Add this topic to your repoTo associate your repository with the parallel-decoding topic, visit your repo's landing page and select "manage topics." |
| You are visitor 01402503 — GeezerVison does not store the pages you look up. Best viewed with Netscape Navigator 4.7 or Internet Explorer 6 at 800×600. No cookies required. |