Deelvin mlc-llm issues - Githubissues

Deelvin / mlc-llm

Enable everyone to develop, optimize and deploy AI models natively on everyone's devices.

https://mlc.ai/mlc-llm

Apache License 2.0

0 stars 0 forks source link

issues

Newest

Newest Most commented Recently updated Oldest Least commented Least recently updated

Scaling parameter optimization for SmoothQuant

#9 Ailurus1 opened 5 months ago
0
any change commit

#8 elvin-n opened 5 months ago
0
Fix token decoding for top logprobs in response

#7 Ailurus1 closed 6 months ago
0
Optimize SmoothQuant alpha per-topology for the best accuracy on Llama2 family models

#6 vvchernov opened 7 months ago
1
Test script for evaluation of matmul error in different pre/post-processing and quantization conditions

#5 vvchernov opened 7 months ago
5
Study SOTA of LLM compression

#4 vvchernov opened 8 months ago
1
Theoretical analysis

#3 vvchernov opened 8 months ago
0
Backlog list

#2 vvchernov opened 8 months ago
0
Calibrate and use matmul error as bias

#1 vvchernov opened 8 months ago
0