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 #2024] falcon model not working. #63207

New Issue
Closed
opened 2026-05-03 12:35:15 -05:00 by GiteaMirror · 3 comments
GiteaMirror commented 2026-05-03 12:35:15 -05:00
Owner
Copy Link

Originally created by @iplayfast on GitHub (Jan 16, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/2024

I've been working with https://github.com/jmorganca/ollama/issues/1691 and found that it consistently dies with falcon.
So I tried falcon on it's own. It died.
So I tried removing falcon and reinstalling it.
Still died.
I can no longer get falcon to work.
I'm on Ollama version 0.1.20

Originally created by @iplayfast on GitHub (Jan 16, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/2024 I've been working with https://github.com/jmorganca/ollama/issues/1691 and found that it consistently dies with falcon. So I tried falcon on it's own. It died. So I tried removing falcon and reinstalling it. Still died. I can no longer get falcon to work. I'm on Ollama version 0.1.20
GiteaMirror added the bug label 2026-05-03 12:35:15 -05:00
GiteaMirror commented 2026-05-03 12:35:27 -05:00
Author
Owner
Copy Link

@EMREOYUN commented on GitHub (Apr 2, 2024):

Successfully reproduced.

Debug server throws CUBLAS_STATUS_NOT_SUPPORTED error and only in Falcon models.
CUDA error: CUBLAS_STATUS_NOT_SUPPORTED current device: 0, in function ggml_cuda_mul_mat_batched_cublas at C:\a\ollama\ollama\llm\llama.cpp\ggml-cuda.cu:10604 cublasGemmBatchedEx(ctx.cublas_handle(), CUBLAS_OP_T, CUBLAS_OP_N, ne01, ne11, ne10, alpha, (const void **) (ptrs_src.get() + 0*ne23), CUDA_R_16F, nb01/nb00, (const void **) (ptrs_src.get() + 1*ne23), CUDA_R_16F, nb11/nb10, beta, ( void **) (ptrs_dst.get() + 0*ne23), cu_data_type, ne01, ne23, cu_compute_type, CUBLAS_GEMM_DEFAULT_TENSOR_OP) GGML_ASSERT: C:\a\ollama\ollama\llm\llama.cpp\ggml-cuda.cu:193: !"CUDA error"

Using:

  • Ollama: 0.1.30 Windows Preview
  • CUDA: nvcc: NVIDIA (R) Cuda compiler driver
    Copyright (c) 2005-2024 NVIDIA Corporation
    Built on Tue_Feb_27_16:28:36_Pacific_Standard_Time_2024
    Cuda compilation tools, release 12.4, V12.4.99
    Build cuda_12.4.r12.4/compiler.33961263_0
  • GPU: NVIDIA RTX 3050 Laptop
  • CPU: Intel i5-11400H
<!-- gh-comment-id:2031673873 --> @EMREOYUN commented on GitHub (Apr 2, 2024): Successfully reproduced. Debug server throws CUBLAS_STATUS_NOT_SUPPORTED error and only in Falcon models. `CUDA error: CUBLAS_STATUS_NOT_SUPPORTED current device: 0, in function ggml_cuda_mul_mat_batched_cublas at C:\a\ollama\ollama\llm\llama.cpp\ggml-cuda.cu:10604 cublasGemmBatchedEx(ctx.cublas_handle(), CUBLAS_OP_T, CUBLAS_OP_N, ne01, ne11, ne10, alpha, (const void **) (ptrs_src.get() + 0*ne23), CUDA_R_16F, nb01/nb00, (const void **) (ptrs_src.get() + 1*ne23), CUDA_R_16F, nb11/nb10, beta, ( void **) (ptrs_dst.get() + 0*ne23), cu_data_type, ne01, ne23, cu_compute_type, CUBLAS_GEMM_DEFAULT_TENSOR_OP) GGML_ASSERT: C:\a\ollama\ollama\llm\llama.cpp\ggml-cuda.cu:193: !"CUDA error"` Using: - Ollama: 0.1.30 Windows Preview - CUDA: nvcc: NVIDIA (R) Cuda compiler driver Copyright (c) 2005-2024 NVIDIA Corporation Built on Tue_Feb_27_16:28:36_Pacific_Standard_Time_2024 Cuda compilation tools, release 12.4, V12.4.99 Build cuda_12.4.r12.4/compiler.33961263_0 - GPU: NVIDIA RTX 3050 Laptop - CPU: Intel i5-11400H
GiteaMirror commented 2026-05-03 12:35:28 -05:00
Author
Owner
Copy Link

@iplayfast commented on GitHub (Apr 2, 2024):

Yup still dead with ollama 0.1.30 linux

<!-- gh-comment-id:2033187270 --> @iplayfast commented on GitHub (Apr 2, 2024): Yup still dead with ollama 0.1.30 linux
GiteaMirror commented 2026-05-03 12:35:29 -05:00
Author
Owner
Copy Link

@pdevine commented on GitHub (May 17, 2024):

We use llama.cpp for the backend runner and it unfortunately dropped support for the original falcon model. There is now the falcon2 model which does work.

<!-- gh-comment-id:2118409444 --> @pdevine commented on GitHub (May 17, 2024): We use llama.cpp for the backend runner and it unfortunately dropped support for the original falcon model. There is now the [falcon2](https://ollama.com/library/falcon2) model which does work.
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#63207
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?