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 #6044] Illegal istruction in ollama_llama_server runner #65820

New Issue
Closed
opened 2026-05-03 22:48:36 -05:00 by GiteaMirror · 2 comments
GiteaMirror commented 2026-05-03 22:48:36 -05:00
Owner
Copy Link

Originally created by @SnowyCoder on GitHub (Jul 29, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/6044

What is the issue?

I tried to run llama3 model with ollama.
Reproduction (with my CPU: AMD Ryzen 7 7735HS)

  1. Start server: ollama serve
  2. Try to run llama3: `ollama run llama3
    (The same error occurs with llama3.1)

The server will execute a new runner with the following arguments:
/tmp/ollama996131774/runners/cpu/ollama_llama_server --model /home/snowy/.ollama/models/blobs/ sha256-6a0746a1ec1aef3e7ec53868f220ff6e389f6f8ef87a01d77c96807de94ca2aa --ctx-size 8192 --batch-size 512 --embedding --log-disable --no-mmap --parallel 4 --port 42857

And the model will fail with the following errors:

llama runner process has terminated: signal: illegal instruction (core dumped)

When opening the runner with GDB, the program crashes when trying to run the following instruction: vmovupd %zmm0,0x13(%rax) (ggml_init+775) that requires AVX512F feature flag.

Complete log:

❯ ollama serve
2024/07/29 12:09:49 routes.go:1099: INFO server config env="map[CUDA_VISIBLE_DEVICES: GPU_DEVICE_ORDINAL: HIP_VISIBLE_DEVICES: HSA_OVERRIDE_GFX_VERSION: OLLAMA_DEBUG:false OLLAMA_FLASH_ATTENTION:false OLLAMA_HOST:http://127.0.0.1:11434 OLLAMA_INTEL_GPU:false OLLAMA_KEEP_ALIVE:5m0s OLLAMA_LLM_LIBRARY: OLLAMA_MAX_LOADED_MODELS:0 OLLAMA_MAX_QUEUE:512 OLLAMA_MODELS:/home/snowy/.ollama/models OLLAMA_NOHISTORY:false OLLAMA_NOPRUNE:false OLLAMA_NUM_PARALLEL:0 OLLAMA_ORIGINS:[http://localhost https://localhost http://localhost:* https://localhost:* http://127.0.0.1 https://127.0.0.1 http://127.0.0.1:* https://127.0.0.1:* http://0.0.0.0 https://0.0.0.0 http://0.0.0.0:* https://0.0.0.0:* app://* file://* tauri://*] OLLAMA_RUNNERS_DIR: OLLAMA_SCHED_SPREAD:false OLLAMA_TMPDIR: ROCR_VISIBLE_DEVICES:]"
time=2024-07-29T12:09:49.854+02:00 level=INFO source=images.go:784 msg="total blobs: 10"
time=2024-07-29T12:09:49.855+02:00 level=INFO source=images.go:791 msg="total unused blobs removed: 0"
time=2024-07-29T12:09:49.855+02:00 level=INFO source=routes.go:1146 msg="Listening on 127.0.0.1:11434 (version 0.3.0)"
time=2024-07-29T12:09:49.855+02:00 level=INFO source=payload.go:30 msg="extracting embedded files" dir=/tmp/ollama996131774/runners
time=2024-07-29T12:09:57.575+02:00 level=INFO source=payload.go:44 msg="Dynamic LLM libraries [cpu rocm]"
time=2024-07-29T12:09:57.575+02:00 level=INFO source=gpu.go:205 msg="looking for compatible GPUs"
time=2024-07-29T12:09:57.657+02:00 level=WARN source=amd_linux.go:58 msg="ollama recommends running the https://www.amd.com/en/support/linux-drivers" error="amdgpu version file missing: /sys/module/amdgpu/version stat /sys/module/amdgpu/version: no such file or directory"
time=2024-07-29T12:09:57.662+02:00 level=WARN source=amd_linux.go:325 msg="amdgpu is not supported" gpu=0 gpu_type=gfx1035 library=/opt/rocm/lib supported_types="[gfx1030 gfx1100 gfx1101 gfx1102 gfx900 gfx906 gfx908 gfx90a gfx940 gfx941 gfx942]"
time=2024-07-29T12:09:57.662+02:00 level=WARN source=amd_linux.go:327 msg="See https://github.com/ollama/ollama/blob/main/docs/gpu.md#overrides for HSA_OVERRIDE_GFX_VERSION usage"
time=2024-07-29T12:09:57.662+02:00 level=INFO source=amd_linux.go:345 msg="no compatible amdgpu devices detected"
time=2024-07-29T12:09:57.662+02:00 level=INFO source=gpu.go:346 msg="no compatible GPUs were discovered"
time=2024-07-29T12:09:57.662+02:00 level=INFO source=types.go:105 msg="inference compute" id=0 library=cpu compute="" driver=0.0 name="" total="13.3 GiB" available="9.1 GiB"
[GIN] 2024/07/29 - 12:09:57 | 200 |      66.764µs |       127.0.0.1 | HEAD     "/"
[GIN] 2024/07/29 - 12:09:57 | 200 |   41.795654ms |       127.0.0.1 | POST     "/api/show"
time=2024-07-29T12:09:57.790+02:00 level=INFO source=memory.go:309 msg="offload to cpu" layers.requested=-1 layers.model=33 layers.offload=0 layers.split="" memory.available="[9.1 GiB]" memory.required.full="5.8 GiB" memory.required.partial="0 B" memory.required.kv="1.0 GiB" memory.required.allocations="[5.8 GiB]" memory.weights.total="4.7 GiB" memory.weights.repeating="4.3 GiB" memory.weights.nonrepeating="411.0 MiB" memory.graph.full="560.0 MiB" memory.graph.partial="677.5 MiB"
time=2024-07-29T12:09:57.792+02:00 level=INFO source=server.go:383 msg="starting llama server" cmd="/tmp/ollama996131774/runners/cpu/ollama_llama_server --model /home/snowy/.ollama/models/blobs/sha256-6a0746a1ec1aef3e7ec53868f220ff6e389f6f8ef87a01d77c96807de94ca2aa --ctx-size 8192 --batch-size 512 --embedding --log-disable --no-mmap --parallel 4 --port 42857"
time=2024-07-29T12:09:57.793+02:00 level=INFO source=sched.go:437 msg="loaded runners" count=1
time=2024-07-29T12:09:57.793+02:00 level=INFO source=server.go:583 msg="waiting for llama runner to start responding"
time=2024-07-29T12:09:57.794+02:00 level=INFO source=server.go:617 msg="waiting for server to become available" status="llm server error"
time=2024-07-29T12:09:58.044+02:00 level=ERROR source=sched.go:443 msg="error loading llama server" error="llama runner process has terminated: signal: illegal instruction (core dumped)"
[GIN] 2024/07/29 - 12:09:58 | 500 |  338.214098ms |       127.0.0.1 | POST     "/api/chat"
[GIN] 2024/07/29 - 12:18:18 | 200 |       63.63µs |       127.0.0.1 | GET      "/api/version"

coredump.zip
cpuinfo.txt

OS

Linux

GPU

AMD

CPU

AMD

Ollama version

0.3.0

Originally created by @SnowyCoder on GitHub (Jul 29, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/6044 ### What is the issue? I tried to run llama3 model with ollama. Reproduction (with my CPU: `AMD Ryzen 7 7735HS`) 1. Start server: `ollama serve` 2. Try to run llama3: `ollama run llama3 (The same error occurs with llama3.1) The server will execute a new runner with the following arguments: ```/tmp/ollama996131774/runners/cpu/ollama_llama_server --model /home/snowy/.ollama/models/blobs/ sha256-6a0746a1ec1aef3e7ec53868f220ff6e389f6f8ef87a01d77c96807de94ca2aa --ctx-size 8192 --batch-size 512 --embedding --log-disable --no-mmap --parallel 4 --port 42857``` And the model will fail with the following errors: ``` llama runner process has terminated: signal: illegal instruction (core dumped) ``` When opening the runner with GDB, the program crashes when trying to run the following instruction: `vmovupd %zmm0,0x13(%rax)` (ggml_init+775) that requires AVX512F feature flag. Complete log: ``` ❯ ollama serve 2024/07/29 12:09:49 routes.go:1099: INFO server config env="map[CUDA_VISIBLE_DEVICES: GPU_DEVICE_ORDINAL: HIP_VISIBLE_DEVICES: HSA_OVERRIDE_GFX_VERSION: OLLAMA_DEBUG:false OLLAMA_FLASH_ATTENTION:false OLLAMA_HOST:http://127.0.0.1:11434 OLLAMA_INTEL_GPU:false OLLAMA_KEEP_ALIVE:5m0s OLLAMA_LLM_LIBRARY: OLLAMA_MAX_LOADED_MODELS:0 OLLAMA_MAX_QUEUE:512 OLLAMA_MODELS:/home/snowy/.ollama/models OLLAMA_NOHISTORY:false OLLAMA_NOPRUNE:false OLLAMA_NUM_PARALLEL:0 OLLAMA_ORIGINS:[http://localhost https://localhost http://localhost:* https://localhost:* http://127.0.0.1 https://127.0.0.1 http://127.0.0.1:* https://127.0.0.1:* http://0.0.0.0 https://0.0.0.0 http://0.0.0.0:* https://0.0.0.0:* app://* file://* tauri://*] OLLAMA_RUNNERS_DIR: OLLAMA_SCHED_SPREAD:false OLLAMA_TMPDIR: ROCR_VISIBLE_DEVICES:]" time=2024-07-29T12:09:49.854+02:00 level=INFO source=images.go:784 msg="total blobs: 10" time=2024-07-29T12:09:49.855+02:00 level=INFO source=images.go:791 msg="total unused blobs removed: 0" time=2024-07-29T12:09:49.855+02:00 level=INFO source=routes.go:1146 msg="Listening on 127.0.0.1:11434 (version 0.3.0)" time=2024-07-29T12:09:49.855+02:00 level=INFO source=payload.go:30 msg="extracting embedded files" dir=/tmp/ollama996131774/runners time=2024-07-29T12:09:57.575+02:00 level=INFO source=payload.go:44 msg="Dynamic LLM libraries [cpu rocm]" time=2024-07-29T12:09:57.575+02:00 level=INFO source=gpu.go:205 msg="looking for compatible GPUs" time=2024-07-29T12:09:57.657+02:00 level=WARN source=amd_linux.go:58 msg="ollama recommends running the https://www.amd.com/en/support/linux-drivers" error="amdgpu version file missing: /sys/module/amdgpu/version stat /sys/module/amdgpu/version: no such file or directory" time=2024-07-29T12:09:57.662+02:00 level=WARN source=amd_linux.go:325 msg="amdgpu is not supported" gpu=0 gpu_type=gfx1035 library=/opt/rocm/lib supported_types="[gfx1030 gfx1100 gfx1101 gfx1102 gfx900 gfx906 gfx908 gfx90a gfx940 gfx941 gfx942]" time=2024-07-29T12:09:57.662+02:00 level=WARN source=amd_linux.go:327 msg="See https://github.com/ollama/ollama/blob/main/docs/gpu.md#overrides for HSA_OVERRIDE_GFX_VERSION usage" time=2024-07-29T12:09:57.662+02:00 level=INFO source=amd_linux.go:345 msg="no compatible amdgpu devices detected" time=2024-07-29T12:09:57.662+02:00 level=INFO source=gpu.go:346 msg="no compatible GPUs were discovered" time=2024-07-29T12:09:57.662+02:00 level=INFO source=types.go:105 msg="inference compute" id=0 library=cpu compute="" driver=0.0 name="" total="13.3 GiB" available="9.1 GiB" [GIN] 2024/07/29 - 12:09:57 | 200 | 66.764µs | 127.0.0.1 | HEAD "/" [GIN] 2024/07/29 - 12:09:57 | 200 | 41.795654ms | 127.0.0.1 | POST "/api/show" time=2024-07-29T12:09:57.790+02:00 level=INFO source=memory.go:309 msg="offload to cpu" layers.requested=-1 layers.model=33 layers.offload=0 layers.split="" memory.available="[9.1 GiB]" memory.required.full="5.8 GiB" memory.required.partial="0 B" memory.required.kv="1.0 GiB" memory.required.allocations="[5.8 GiB]" memory.weights.total="4.7 GiB" memory.weights.repeating="4.3 GiB" memory.weights.nonrepeating="411.0 MiB" memory.graph.full="560.0 MiB" memory.graph.partial="677.5 MiB" time=2024-07-29T12:09:57.792+02:00 level=INFO source=server.go:383 msg="starting llama server" cmd="/tmp/ollama996131774/runners/cpu/ollama_llama_server --model /home/snowy/.ollama/models/blobs/sha256-6a0746a1ec1aef3e7ec53868f220ff6e389f6f8ef87a01d77c96807de94ca2aa --ctx-size 8192 --batch-size 512 --embedding --log-disable --no-mmap --parallel 4 --port 42857" time=2024-07-29T12:09:57.793+02:00 level=INFO source=sched.go:437 msg="loaded runners" count=1 time=2024-07-29T12:09:57.793+02:00 level=INFO source=server.go:583 msg="waiting for llama runner to start responding" time=2024-07-29T12:09:57.794+02:00 level=INFO source=server.go:617 msg="waiting for server to become available" status="llm server error" time=2024-07-29T12:09:58.044+02:00 level=ERROR source=sched.go:443 msg="error loading llama server" error="llama runner process has terminated: signal: illegal instruction (core dumped)" [GIN] 2024/07/29 - 12:09:58 | 500 | 338.214098ms | 127.0.0.1 | POST "/api/chat" [GIN] 2024/07/29 - 12:18:18 | 200 | 63.63µs | 127.0.0.1 | GET "/api/version" ``` [coredump.zip](https://github.com/user-attachments/files/16411350/coredump.zip) [cpuinfo.txt](https://github.com/user-attachments/files/16411356/cpuinfo.txt) ### OS Linux ### GPU AMD ### CPU AMD ### Ollama version 0.3.0
GiteaMirror added the bug label 2026-05-03 22:48:36 -05:00
GiteaMirror commented 2026-05-03 22:48:45 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Jul 29, 2024):

https://github.com/ggerganov/llama.cpp/issues/8734

<!-- gh-comment-id:2255596125 --> @rick-github commented on GitHub (Jul 29, 2024): https://github.com/ggerganov/llama.cpp/issues/8734
GiteaMirror commented 2026-05-03 22:48:48 -05:00
Author
Owner
Copy Link

@SnowyCoder commented on GitHub (Jul 29, 2024):

Thanks, I'll add details in that issue

<!-- gh-comment-id:2255599102 --> @SnowyCoder commented on GitHub (Jul 29, 2024): Thanks, I'll add details in that issue
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#65820
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?