Alex Romashko issues

Repositories
Issues
Comments

Results 2 issues of


                                            Alex Romashko

Parallel infer on multiple GPUs

Would be nice to make HCube inferencw faster using parallel model deploy into 2+ GPUs. Any options ?

[WONTFIX]: Investigation and gathering knowledge on OLLAMA local different models prompts output

### Reason for won't fix Investigation and gathering knowledge ### Decision maker Alex Romashko ### Additional context Please share here you details on running different ollama models with the tool

wontfix