Language Models
chiennv2000/orthrus
[NeurIPS 2026 Spotlight] Fast, lossless LLM inference via dual-view diffusion decoding.
PythonMITupdated Aug 12, 2026
🏆 #6,002 overall#1232 of 1,375 in Language Models
ZinYY /OnlineSPEC
[ICML 2026] When Drafts Evolve: Speculative Decoding Meets Online Learning
$ git clone https://github.com/ZinYY/OnlineSPEC.gitStars
127
127
This week
—
Forks
20
20
Language
Python
License
None
Created
Mar 13, 2026
0.7 years old
Last push
Jul 27, 2026
Categories
More in Language Models
Language Models
SqueezeAILab/LLMCompiler
[ICML 2024] LLMCompiler: An LLM Compiler for Parallel Function Calling
🧠 Natural Language Processing
PythonMITupdated Jul 10, 2024
Language Models
SqueezeAILab/SqueezeLLM
[ICML 2024] SqueezeLLM: Dense-and-Sparse Quantization
🧠 Natural Language Processing
PythonMITupdated Aug 13, 2024
Language Models
SqueezeAILab/KVQuant
[NeurIPS 2024] KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization
🧠 Natural Language Processing
Pythonno licenseupdated Aug 13, 2024
Language Models
ZinYY/AdaFlash
[COLMW'26 Spotlight] AdaFlash: Adaptive Speculative Decoding via On-Policy Distilled Diffusion Drafters
Pythonno licenseupdated Oct 28, 2026
Language Models
THU-BPM/RLCSD
Source code of paper "RLCSD: Reinforcement Learning with Contrastive On-Policy Self-Distillation"
PythonMITupdated Sep 14, 2026
Data from GitHub · snapshot Nov 13, 2026