Content-Length: 216002 | pFad | http://github.com/NVIDIA/TensorRT-LLM/actions/runs/12782886220

06 Deepseek-v3 int4 weight only inference outputs garbage words with TP 8 on nvidia H20 GPU · NVIDIA/TensorRT-LLM@0d0583a · GitHub
Skip to content
Blossom-CI

Deepseek-v3 int4 weight only inference outputs garbage words with TP 8 on nvidia H20 GPU #400

Sign in to view logs

Deepseek-v3 int4 weight only inference outputs garbage words with TP 8 on nvidia H20 GPU

Deepseek-v3 int4 weight only inference outputs garbage words with TP 8 on nvidia H20 GPU #400

Triggered via issue January 15, 2025 06:36
@handokuhandoku
commented on #2683 0d0583a
Status Skipped
Total duration 4s
Artifacts –

blossom-ci.yml

on: issue_comment
Authorization
0s
Authorization
Upload log
0s
Upload log
Vulnerability scan
0s
Vulnerability scan
Start ci job
0s
Start ci job
Fit to window
Zoom out
Zoom in








ApplySandwichStrip

pFad - (p)hone/(F)rame/(a)nonymizer/(d)eclutterfier!      Saves Data!


--- a PPN by Garber Painting Akron. With Image Size Reduction included!

Fetched URL: http://github.com/NVIDIA/TensorRT-LLM/actions/runs/12782886220

Alternative Proxies:

Alternative Proxy

pFad Proxy

pFad v3 Proxy

pFad v4 Proxy