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 #3023] Mamba State Space Models Integration #1859

New Issue
Open
opened 2026-04-12 11:55:21 -05:00 by GiteaMirror · 7 comments
GiteaMirror commented 2026-04-12 11:55:21 -05:00
Owner
Copy Link

Originally created by @MarcellM01 on GitHub (Mar 9, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/3023

There has been a completed merge of mamba model support over at Ilama.ccp, would it be possible to implement these into Ollama as well?

Merged PR: https://github.com/ggerganov/llama.cpp/pull/5328

Model examples: https://huggingface.co/collections/Q-bert/mamba-65869481595e25821853d20d

Originally created by @MarcellM01 on GitHub (Mar 9, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/3023 There has been a completed merge of mamba model support over at Ilama.ccp, would it be possible to implement these into Ollama as well? Merged PR: https://github.com/ggerganov/llama.cpp/pull/5328 Model examples: https://huggingface.co/collections/Q-bert/mamba-65869481595e25821853d20d
GiteaMirror added the model label 2026-04-12 11:55:21 -05:00
GiteaMirror commented 2026-04-12 11:55:22 -05:00
Author
Owner
Copy Link

@ekianjo commented on GitHub (Mar 10, 2024):

Yeah, waiting for this integration as well

<!-- gh-comment-id:1987110449 --> @ekianjo commented on GitHub (Mar 10, 2024): Yeah, waiting for this integration as well
GiteaMirror commented 2026-04-12 11:55:23 -05:00
Author
Owner
Copy Link

@BradKML commented on GitHub (Mar 12, 2024):

Seconding this, also with RWKV (Eagle) and other fast LLMs like RetNet or H3/S4 https://github.com/ollama/ollama/issues/1612

P.S. Jamba is related to this as well https://github.com/ollama/ollama/issues/3399

<!-- gh-comment-id:1990963471 --> @BradKML commented on GitHub (Mar 12, 2024): Seconding this, also with RWKV (Eagle) and other fast LLMs like RetNet or H3/S4 https://github.com/ollama/ollama/issues/1612 P.S. Jamba is related to this as well https://github.com/ollama/ollama/issues/3399
GiteaMirror commented 2026-04-12 11:55:23 -05:00
Author
Owner
Copy Link

@skyler14 commented on GitHub (May 2, 2024):

Has there been any movement on this in the last month?

<!-- gh-comment-id:2089756620 --> @skyler14 commented on GitHub (May 2, 2024): Has there been any movement on this in the last month?
GiteaMirror commented 2026-04-12 11:55:24 -05:00
Author
Owner
Copy Link

@skyler14 commented on GitHub (May 16, 2024):

There is a one file implementation of base Mamba that was written here, might be very easy to build an OpenAI style wrapper around it.

https://github.com/johnma2006/mamba-minimal

Since there are some rising architectures that seem to do token free extraction it might be interesting to extend a small amount to those tasks

<!-- gh-comment-id:2115452856 --> @skyler14 commented on GitHub (May 16, 2024): There is a one file implementation of base Mamba that was written here, might be very easy to build an OpenAI style wrapper around it. https://github.com/johnma2006/mamba-minimal Since there are some rising architectures that seem to do token free extraction it might be interesting to extend a small amount to those tasks
GiteaMirror commented 2026-04-12 11:55:25 -05:00
Author
Owner
Copy Link

@aretrace commented on GitHub (Sep 9, 2024):

Any update?

<!-- gh-comment-id:2336962047 --> @aretrace commented on GitHub (Sep 9, 2024): Any update?
GiteaMirror commented 2026-04-12 11:55:25 -05:00
Author
Owner
Copy Link

@hg0428 commented on GitHub (Oct 1, 2024):

Any update?

<!-- gh-comment-id:2384671869 --> @hg0428 commented on GitHub (Oct 1, 2024): Any update?
GiteaMirror commented 2026-04-12 11:55:26 -05:00
Author
Owner
Copy Link

@gabe-l-hart commented on GitHub (Jul 14, 2025):

Hi folks. I've got a draft bumping llama.cpp that extends support for mamba, and adds support for mamba2, falcon-h1, granite4 and a number of other recurrent/hybrid-recurrent models. As with all llama.cpp changes, there are a number of additional changes along for the ride, so any additional help testing models on the draft would be much appreciated.

<!-- gh-comment-id:3069938024 --> @gabe-l-hart commented on GitHub (Jul 14, 2025): Hi folks. I've got [a draft](https://github.com/ollama/ollama/pull/11195) bumping `llama.cpp` that extends support for `mamba`, and adds support for `mamba2`, `falcon-h1`, `granite4` and a number of other recurrent/hybrid-recurrent models. As with all `llama.cpp` changes, there are a number of additional changes along for the ride, so any additional help testing models on the draft would be much appreciated.
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 model
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#1859
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?