Skip to content
New issue

Have a question about this project? # for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “#”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? # to your account

fix: correct gpu info list #1944

Merged
merged 3 commits into from
Feb 10, 2025
Merged

fix: correct gpu info list #1944

merged 3 commits into from
Feb 10, 2025

Conversation

vansangpfiev
Copy link
Contributor

Describe Your Changes

This pull request includes updates to the GetGPUInfo function in the engine/utils/hardware/gpu_info.h file. The changes improve the handling of GPU information by incorporating additional data from Vulkan GPUs when available and ensuring that NVIDIA GPU information is used as a fallback.

Key changes include:

  • Improved handling of GPU information by checking if Vulkan GPU data is available and using it if present, otherwise falling back to NVIDIA GPU data.
  • Added logic to populate a vector with NVIDIA GPU information when Vulkan GPU data is not available, including details such as driver version, compute capability, and VRAM.

Fixes Issues

  • Closes #
  • Closes #

Self Checklist

  • Added relevant comments, esp in complex areas
  • Updated docs (for bug fixes / features)
  • Created issues for follow-up changes or refactoring needed

@vansangpfiev vansangpfiev marked this pull request as ready for review February 10, 2025 02:30
@vansangpfiev vansangpfiev merged commit 32af9df into dev Feb 10, 2025
8 checks passed
@vansangpfiev vansangpfiev deleted the fix/gpu-list branch February 10, 2025 04:55
vansangpfiev added a commit that referenced this pull request Feb 10, 2025
* fix: correct gpu info list

* chore: cleanup

---------

Co-authored-by: vansangpfiev <sang@jan.ai>
vansangpfiev added a commit that referenced this pull request Feb 18, 2025
* feat: AMD hardware API (#1797)

* feat: add amd gpu windows

* chore: remove unused code

* feat: get amd gpus

* fix: clean

* chore: cleanup

* fix: set activate

* fix: build windows

* feat: linux

* fix: add patches

* fix: map cuda gpus

* fix: build

* chore: docs

* fix: build

* chore: clean up

* fix: build

* fix: build

* chore: pack vulkan windows

* chore: vulkan linux

---------

Co-authored-by: vansangpfiev <sang@jan.ai>

* fix: add cpu usage (#1868)

Co-authored-by: vansangpfiev <sang@jan.ai>

* fix: PATCH method for Thread and Messages management (#1923)

Co-authored-by: vansangpfiev <sang@jan.ai>

* fix: ignore compute_cap if not present (#1866)

* fix: ignore compute_cap if not present

* fix: correct gpu info

* fix: remove check for toolkit version

---------

Co-authored-by: vansangpfiev <sang@jan.ai>

* fix: models.cc: symlinked model deletion shouldn't remove original file (#1918)

Co-authored-by: vansangpfiev <vansangpfiev@gmail.com>

* fix: correct gpu info list (#1944)

* fix: correct gpu info list

* chore: cleanup

---------

Co-authored-by: vansangpfiev <sang@jan.ai>

* fix: gpu: filter out llvmpipe

* fix: add vendor in gpu info (#1952)

Co-authored-by: vansangpfiev <sang@jan.ai>

* fix: correct get server name method (#1953)

Co-authored-by: vansangpfiev <sang@jan.ai>

* fix: map nvidia and vulkan uuid (#1954)

Co-authored-by: vansangpfiev <sang@jan.ai>

* fix: permission issue for default drogon uploads folder (#1870)

Co-authored-by: vansangpfiev <sang@jan.ai>

* chore: change timeout

* fix: make get hardware info function thread-safe (#1956)

Co-authored-by: vansangpfiev <sang@jan.ai>

* fix: cache data for gpu information (#1959)

* fix: wrap vulkan gpu function

* fix: init

* fix: cpu usage

* fix: build windows

* fix: buld macos

---------

Co-authored-by: vansangpfiev <sang@jan.ai>

* fix: handle path with space (#1963)

* fix: unload engine before updating (#1970)

Co-authored-by: sangjanai <sang@jan.ai>

* fix: auto-reload model for remote engine (#1971)

Co-authored-by: sangjanai <sang@jan.ai>

* fix: use updated configuration for remote model when reload (#1972)

Co-authored-by: sangjanai <sang@jan.ai>

* fix: correct engine interface order (#1974)

Co-authored-by: sangjanai <sang@jan.ai>

* fix: improve error handling for remote engine (#1975)

Co-authored-by: sangjanai <sang@jan.ai>

* fix: temporarily remove model setting recommendation (#1977)

Co-authored-by: sangjanai <sang@jan.ai>

---------

Co-authored-by: vansangpfiev <sang@jan.ai>
Co-authored-by: OHaiiBuzzle <23693150+ohaiibuzzle@users.noreply.github.com>
# for free to join this conversation on GitHub. Already have an account? # to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants