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 #9984] Add support for array for head count GGUF KV #32301

New Issue
Closed
opened 2026-04-22 13:25:41 -05:00 by GiteaMirror · 2 comments
GiteaMirror commented 2026-04-22 13:25:41 -05:00
Owner
Copy Link

Originally created by @ngxson on GitHub (Mar 25, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/9984

Originally assigned to: @drifkin on GitHub.

What is the issue?

Ref bug: https://huggingface.co/bartowski/nvidia_Llama-3_3-Nemotron-Super-49B-v1-GGUF/discussions/3

Some architectures have head_count and head_count_kv as an array of int, because each layer in the model can have different number of heads.

Image

Link to relevant LOC: 131f0355a5/fs/ggml/ggml.go (L55)

However, since ollama only support Uint for these KV, EstimateGPULayers currently fails on certain models. Please see the attached log

Relevant log output

panic: interface conversion: interface {} is *ggml.array, not uint32

goroutine 27 [running]:
github.com/ollama/ollama/fs/ggml.keyValue[...](0xc00010a570, {0x7ff67b6bf1a3, 0x14}, {0xc000624548, 0x1, 0x7ff67a55e960})
C:/a/ollama/ollama/fs/ggml/ggml.go:146 +0x2de
github.com/ollama/ollama/fs/ggml.KV.Uint(...)
C:/a/ollama/ollama/fs/ggml/ggml.go:96
github.com/ollama/ollama/fs/ggml.KV.HeadCount(...)
C:/a/ollama/ollama/fs/ggml/ggml.go:56
github.com/ollama/ollama/fs/ggml.GGML.GraphSize({{0x7ff67b874828?, 0xc000726000?}, {0x7ff67b8747d8?, 0xc00018d808?}}, 0x20000, 0x200, {0x0, 0x0})
C:/a/ollama/ollama/fs/ggml/ggml.go:418 +0x137
github.com/ollama/ollama/llm.EstimateGPULayers({_, _, _}, , {, _, _}, {{0x20000, 0x200, 0xffffffffffffffff, ...}, ...})
C:/a/ollama/ollama/llm/memory.go:140 +0x659
github.com/ollama/ollama/llm.PredictServerFit({0xc00004bba8?, 0x7ff67a540f2e?, 0xc00004b8c0?}, 0xc000350060, {0xc00004b908?, _, _}, {0x0, 0x0, 0x0}, ...)
C:/a/ollama/ollama/llm/memory.go:23 +0xbd
github.com/ollama/ollama/server.pickBestFullFitByLibrary(0xc000570000, 0xc000350060, {0xc000160600?, 0x2?, 0x2?}, 0xc00004bcf8)
C:/a/ollama/ollama/server/sched.go:714 +0x6f3
github.com/ollama/ollama/server.(*Scheduler).processPending(0xc00009a8a0, {0x7ff67b878800, 0xc000726ff0})
C:/a/ollama/ollama/server/sched.go:226 +0xe6b
github.com/ollama/ollama/server.(*Scheduler).Run.func1()
C:/a/ollama/ollama/server/sched.go:108 +0x1f
created by github.com/ollama/ollama/server.(*Scheduler).Run in goroutine 1
C:/a/ollama/ollama/server/sched.go:107 +0xb1

OS

Windows

GPU

No response

CPU

No response

Ollama version

No response

Originally created by @ngxson on GitHub (Mar 25, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/9984 Originally assigned to: @drifkin on GitHub. ### What is the issue? Ref bug: https://huggingface.co/bartowski/nvidia_Llama-3_3-Nemotron-Super-49B-v1-GGUF/discussions/3 Some architectures have head_count and head_count_kv as an array of int, because each layer in the model can have different number of heads. <img width="480" alt="Image" src="https://github.com/user-attachments/assets/f0e4a80f-4828-4427-aba9-ce53d9633c26" /> Link to relevant LOC: https://github.com/ollama/ollama/blob/131f0355a59f4840b057fb8f3c2e59e456f91041/fs/ggml/ggml.go#L55 However, since ollama only support Uint for these KV, `EstimateGPULayers` currently fails on certain models. Please see the attached log ### Relevant log output ```shell panic: interface conversion: interface {} is *ggml.array, not uint32 goroutine 27 [running]: github.com/ollama/ollama/fs/ggml.keyValue[...](0xc00010a570, {0x7ff67b6bf1a3, 0x14}, {0xc000624548, 0x1, 0x7ff67a55e960}) C:/a/ollama/ollama/fs/ggml/ggml.go:146 +0x2de github.com/ollama/ollama/fs/ggml.KV.Uint(...) C:/a/ollama/ollama/fs/ggml/ggml.go:96 github.com/ollama/ollama/fs/ggml.KV.HeadCount(...) C:/a/ollama/ollama/fs/ggml/ggml.go:56 github.com/ollama/ollama/fs/ggml.GGML.GraphSize({{0x7ff67b874828?, 0xc000726000?}, {0x7ff67b8747d8?, 0xc00018d808?}}, 0x20000, 0x200, {0x0, 0x0}) C:/a/ollama/ollama/fs/ggml/ggml.go:418 +0x137 github.com/ollama/ollama/llm.EstimateGPULayers({_, _, _}, , {, _, _}, {{0x20000, 0x200, 0xffffffffffffffff, ...}, ...}) C:/a/ollama/ollama/llm/memory.go:140 +0x659 github.com/ollama/ollama/llm.PredictServerFit({0xc00004bba8?, 0x7ff67a540f2e?, 0xc00004b8c0?}, 0xc000350060, {0xc00004b908?, _, _}, {0x0, 0x0, 0x0}, ...) C:/a/ollama/ollama/llm/memory.go:23 +0xbd github.com/ollama/ollama/server.pickBestFullFitByLibrary(0xc000570000, 0xc000350060, {0xc000160600?, 0x2?, 0x2?}, 0xc00004bcf8) C:/a/ollama/ollama/server/sched.go:714 +0x6f3 github.com/ollama/ollama/server.(*Scheduler).processPending(0xc00009a8a0, {0x7ff67b878800, 0xc000726ff0}) C:/a/ollama/ollama/server/sched.go:226 +0xe6b github.com/ollama/ollama/server.(*Scheduler).Run.func1() C:/a/ollama/ollama/server/sched.go:108 +0x1f created by github.com/ollama/ollama/server.(*Scheduler).Run in goroutine 1 C:/a/ollama/ollama/server/sched.go:107 +0xb1 ``` ### OS Windows ### GPU _No response_ ### CPU _No response_ ### Ollama version _No response_
GiteaMirror added the bug label 2026-04-22 13:25:41 -05:00
GiteaMirror commented 2026-04-22 13:25:43 -05:00
Author
Owner
Copy Link

@dpk-it commented on GitHub (Mar 25, 2025):

related to https://github.com/ollama/ollama/issues/8460

<!-- gh-comment-id:2752067335 --> @dpk-it commented on GitHub (Mar 25, 2025): related to https://github.com/ollama/ollama/issues/8460
GiteaMirror commented 2026-04-22 13:25:44 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Apr 12, 2025):

Also needed for OpenELM (#3910).

<!-- gh-comment-id:2799065696 --> @rick-github commented on GitHub (Apr 12, 2025): Also needed for OpenELM (#3910).
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 bug
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#32301
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?