cppnomic-ai/gpt4all #3481Not a task: not reproduced

Add support for GPUs with cuda compute capability 5.0

envgap__nomic-ai__gpt4all-3481

Original GitHub issue ↗Dated source checkout ↗Opened 2025-02-10

01 / FAILURE SIGNATURE

As reported upstream

No identifying execution failure has been captured.

Not a benchmark task.

In a clean container the reported failure did not reproduce, or the known fix did not make the project run.

02 / ENVIRONMENT RECIPE

Base commit: b83d06e67f3e794706f1d8437b69673d3378029e
Manifest: gpt4all-backend/CMakeLists.txt
Reproduce: Awaiting issue-specific recipe
Run under trace: Awaiting a meaningful runtime command

03 / ORIGINAL ISSUE TEXT

nomic-ai/gpt4all #3481 · read the original issue

The current version is incompatible with GPUs with cuda compute capability 5.0(NVIDIA Maxwell architecture), which will cause a crash when trying to chat with models on these devices. Please update the cuda llama backend to support it.

Continue on GitHub ↗

04 / LABELS

Labels from the report text only; not yet run

No supported category has been assigned.

Label rules and the text that matched

[]