github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-07 00:22:43 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #8332] Allow set the type of K/V cache separately #31100

New Issue
Open
opened 2026-04-22 11:15:39 -05:00 by GiteaMirror · 2 comments
GiteaMirror commented 2026-04-22 11:15:39 -05:00
Owner
Copy Link

Originally created by @ag2s20150909 on GitHub (Jan 7, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/8332

Allow set the type of K/V cache separately

On Qwen2-7B,
when K/V cache both q4_0 produces weird results.
when k is q4_0 and v is q8_0 produces weird results.
when k is q8_0 and v is q4_0 produces normal results.

Originally created by @ag2s20150909 on GitHub (Jan 7, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/8332 Allow set the type of K/V cache separately On Qwen2-7B, when K/V cache both `q4_0` produces weird results. when k is `q4_0` and v is `q8_0` produces weird results. when k is `q8_0` and v is `q4_0` produces normal results.
GiteaMirror added the feature request label 2026-04-22 11:15:39 -05:00
GiteaMirror commented 2026-04-22 11:15:40 -05:00
Author
Owner
Copy Link

@youcefs21 commented on GitHub (Jan 21, 2025):

I feel like the same can be said about DeepSeek-R1-Distill-Qwen-32B

<!-- gh-comment-id:2604823072 --> @youcefs21 commented on GitHub (Jan 21, 2025): I feel like the same can be said about DeepSeek-R1-Distill-Qwen-32B
GiteaMirror commented 2026-04-22 11:15:40 -05:00
Author
Owner
Copy Link

@Kaylebor commented on GitHub (Mar 4, 2026):

For starters it'd be nice to at least be able to set them per model https://github.com/ollama/ollama/pull/7983

<!-- gh-comment-id:4000796191 --> @Kaylebor commented on GitHub (Mar 4, 2026): For starters it'd be nice to at least be able to set them per model https://github.com/ollama/ollama/pull/7983
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#31100
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?