github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-06 16:11:34 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #6569] TensorRT Support #66173

New Issue
Open
opened 2026-05-04 00:28:14 -05:00 by GiteaMirror · 2 comments
GiteaMirror commented 2026-05-04 00:28:14 -05:00
Owner
Copy Link

Originally created by @JonahMMay on GitHub (Aug 30, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/6569

Does ollama leverage TensorRT and if not, can support for it be added?

Originally created by @JonahMMay on GitHub (Aug 30, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/6569 Does ollama leverage TensorRT and if not, can support for it be added?
GiteaMirror added the feature request label 2026-05-04 00:28:14 -05:00
GiteaMirror commented 2026-05-04 00:28:16 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Aug 30, 2024):

That would be a feature request for llama.cpp.

<!-- gh-comment-id:2322164426 --> @rick-github commented on GitHub (Aug 30, 2024): That would be a feature request for [llama.cpp](https://github.com/ggerganov/llama.cpp/issues).
GiteaMirror commented 2026-05-04 00:28:18 -05:00
Author
Owner
Copy Link

@AbhiAbzs commented on GitHub (Jan 25, 2025):

Jan.ai have already added support for TensorRT, along side Llama.cpp engine, if its possible can please also add the support for TensorRT as its benchmark seems very promising for inferencing. I tested it once in case of FaceFusion and after the initial load time it reduces the inferening time by more then 4x.
I don't know if its technically feasible to add this or not but it seems promising.
https://jan.ai/post/benchmarking-nvidia-tensorrt-llm

<!-- gh-comment-id:2614055183 --> @AbhiAbzs commented on GitHub (Jan 25, 2025): Jan.ai have already added support for TensorRT, along side Llama.cpp engine, if its possible can please also add the support for TensorRT as its benchmark seems very promising for inferencing. I tested it once in case of FaceFusion and after the initial load time it reduces the inferening time by more then 4x. I don't know if its technically feasible to add this or not but it seems promising. https://jan.ai/post/benchmarking-nvidia-tensorrt-llm
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
amd
api
app
bug
build
cli
cloud
compatibility
context-length
create
docker
documentation
embeddings
feature request
feedback wanted
good first issue
gpt-oss
gpu
harmony
help wanted
image
install
intel
js
launch
linux
macos
memory
mlx
model
needs more info
networking
nvidia
ollama.com
performance
pull-request
Mirrored from GitHub Pull Request
 python
question
registry
rendering
thinking
tools
top
vulkan
windows
wsl
No Label feature request
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
GiteaMirror ninjasurge
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#66173
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?