github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-07-16 13:19:40 -05:00
Code Issues 16.9k Packages Projects Releases 122 Wiki Activity

[GH-ISSUE #6860] It used to work on 4 GPUs with 12.2MiG and one GPU with 4MiB, now it dies on the smaller VRAM GPU #50841

New Issue
Closed
opened 2026-04-28 17:14:24 -05:00 by GiteaMirror · 0 comments
GiteaMirror commented 2026-04-28 17:14:24 -05:00
Owner
Copy Link

Originally created by @phalexo on GitHub (Sep 18, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/6860

What is the issue?

llama_new_context_with_model: KV self size = 5120.00 MiB, K (f16): 2560.00 MiB, V (f16): 2560.00 MiB
llama_new_context_with_model: CUDA_Host output buffer size = 0.49 MiB
llama_new_context_with_model: pipeline parallelism enabled (n_copies=4)
ggml_backend_cuda_buffer_type_alloc_buffer: allocating 144.00 MiB on device 4: cudaMalloc failed: out of memory
ggml_gallocr_reserve_n: failed to allocate CUDA4 buffer of size 150995968
llama_new_context_with_model: failed to allocate compute buffers
Traceback (most recent call last):
File "/home/developer/PROJECTS/AiderTest/langchain_demo.py", line 19, in
llm = LlamaCpp(
^^^^^^^^^
File "/home/developer/mambaforge/envs/Aider/lib/python3.11/site-packages/langchain_core/load/serializable.py", line 112, in init
super().init(*args, **kwargs)
File "/home/developer/mambaforge/envs/Aider/lib/python3.11/site-packages/pydantic/main.py", line 212, in init
validated_self = self.pydantic_validator.validate_python(data, self_instance=self)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
pydantic_core._pydantic_core.ValidationError: 1 validation error for LlamaCpp
Value error, Could not load Llama model from path: /opt/data/bullerwins/Meta-Llama-3.1-70B-Instruct-GGUF/Meta-Llama-3.1-70B-Instruct-Q5_K_S.gguf. Received error Failed to create llama_context [type=value_error, input_value={'model_path': '/opt/data...: None, 'grammar': None}, input_type=dict]
For further information visit https://errors.pydantic.dev/2.9/v/value_error

OS

Linux

GPU

Nvidia

CPU

Intel

Ollama version

Freshly built from source.

Originally created by @phalexo on GitHub (Sep 18, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/6860 ### What is the issue? llama_new_context_with_model: KV self size = 5120.00 MiB, K (f16): 2560.00 MiB, V (f16): 2560.00 MiB llama_new_context_with_model: CUDA_Host output buffer size = 0.49 MiB llama_new_context_with_model: pipeline parallelism enabled (n_copies=4) ggml_backend_cuda_buffer_type_alloc_buffer: allocating 144.00 MiB on device 4: cudaMalloc failed: out of memory ggml_gallocr_reserve_n: failed to allocate CUDA4 buffer of size 150995968 llama_new_context_with_model: failed to allocate compute buffers Traceback (most recent call last): File "/home/developer/PROJECTS/AiderTest/langchain_demo.py", line 19, in <module> llm = LlamaCpp( ^^^^^^^^^ File "/home/developer/mambaforge/envs/Aider/lib/python3.11/site-packages/langchain_core/load/serializable.py", line 112, in __init__ super().__init__(*args, **kwargs) File "/home/developer/mambaforge/envs/Aider/lib/python3.11/site-packages/pydantic/main.py", line 212, in __init__ validated_self = self.__pydantic_validator__.validate_python(data, self_instance=self) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ pydantic_core._pydantic_core.ValidationError: 1 validation error for LlamaCpp Value error, Could not load Llama model from path: /opt/data/bullerwins/Meta-Llama-3.1-70B-Instruct-GGUF/Meta-Llama-3.1-70B-Instruct-Q5_K_S.gguf. Received error Failed to create llama_context [type=value_error, input_value={'model_path': '/opt/data...: None, 'grammar': None}, input_type=dict] For further information visit https://errors.pydantic.dev/2.9/v/value_error ### OS Linux ### GPU Nvidia ### CPU Intel ### Ollama version Freshly built from source.
GiteaMirror added the bug label 2026-04-28 17:14:24 -05:00
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#50841
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?