github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-22 13:42:25 -05:00
Code Issues 16.9k Packages Projects Releases 122 Wiki Activity

[GH-ISSUE #13681] GFX1151 TTM setting is not detected #34743

New Issue
Open
opened 2026-04-22 18:34:09 -05:00 by GiteaMirror · 0 comments
GiteaMirror commented 2026-04-22 18:34:09 -05:00
Owner
Copy Link

Originally created by @na-g on GitHub (Jan 12, 2026).
Original GitHub issue: https://github.com/ollama/ollama/issues/13681

What is the issue?

I am running Ubuntu 25.10 (GNU/Linux 6.17.0-8-generic x86_64). According to amd-ttm I have a TTM page limit of 96GB.

$ amd-ttm
💻 Current TTM pages limit: 25165824 pages (96.00 GB)
💻 Total system memory: 122.84 GB

My ollama version is 0.13.5.

$ ollama --version
ollama version is 0.13.5

The ROCm provider sees the 512MB allocated in the BIOS. The Vulkan provider sees 64 of the 96GB.

I am happy to add whatever additional information may be helpful.

Relevant log output

Using no OLLAMA_LLM_LIBRARY

$ sudo journalctl -fu ollama.service
Jan 11 19:54:13 ark ollama[4493]: time=2026-01-11T19:54:13.479-08:00 level=INFO source=routes.go:1607 msg="Listening on [::]:11434 (version 0.13.5)"
Jan 11 19:54:13 ark ollama[4493]: time=2026-01-11T19:54:13.481-08:00 level=INFO source=runner.go:67 msg="discovering available GPUs..."
Jan 11 19:54:13 ark ollama[4493]: time=2026-01-11T19:54:13.483-08:00 level=INFO source=server.go:429 msg="starting runner" cmd="/usr/local/bin/ollama runner --ollama-engine --port 44333"
Jan 11 19:54:13 ark ollama[4493]: time=2026-01-11T19:54:13.512-08:00 level=INFO source=server.go:429 msg="starting runner" cmd="/usr/local/bin/ollama runner --ollama-engine --port 34305"
Jan 11 19:54:14 ark ollama[4493]: time=2026-01-11T19:54:14.714-08:00 level=INFO source=runner.go:106 msg="experimental Vulkan support disabled.  To enable, set OLLAMA_VULKAN=1"
Jan 11 19:54:14 ark ollama[4493]: time=2026-01-11T19:54:14.714-08:00 level=INFO source=server.go:429 msg="starting runner" cmd="/usr/local/bin/ollama runner --ollama-engine --port 37913"
Jan 11 19:54:14 ark ollama[4493]: time=2026-01-11T19:54:14.733-08:00 level=INFO source=server.go:429 msg="starting runner" cmd="/usr/local/bin/ollama runner --ollama-engine --port 32935"
Jan 11 19:54:15 ark ollama[4493]: time=2026-01-11T19:54:15.366-08:00 level=INFO source=types.go:42 msg="inference compute" id=0 filter_id=0 library=ROCm compute=gfx1151 name=ROCm0 description="AMD Radeon Graphics" libdirs=ollama,rocm driver=60342.13 pci_id=0000:c2:00.0 type=iGPU total="512.0 MiB" available="67.4 MiB"
Jan 11 19:54:15 ark ollama[4493]: time=2026-01-11T19:54:15.366-08:00 level=INFO source=routes.go:1648 msg="entering low vram mode" "total vram"="512.0 MiB" threshold="20.0 GiB"
Jan 11 19:56:17 ark ollama[4493]: [GIN] 2026/01/11 - 19:56:17 | 200 |   35.498192ms |       127.0.0.1 | GET      "/api/version"

=====================================================================================

Using OLLAMA_VULKAN=1 and OLLAMA_LLM_LIBRARY=vulkan
$ sudo journalctl -fu ollama
...
Jan 11 20:00:02 ark systemd[1]: Started ollama.service - Ollama Service.
Jan 11 20:00:02 ark ollama[4957]: time=2026-01-11T20:00:02.993-08:00 level=INFO source=routes.go:1554 msg="server config" env="map[CUDA_VISIBLE_DEVICES: GGML_VK_VISIBLE_DEVICES: GPU_DEVICE_ORDINAL: HIP_VISIBLE_DEVICES: HSA_OVERRIDE_GFX_VERSION: HTTPS_PROXY: HTTP_PROXY: NO_PROXY: OLLAMA_CONTEXT_LENGTH:4096 OLLAMA_DEBUG:INFO OLLAMA_FLASH_ATTENTION:false OLLAMA_GPU_OVERHEAD:0 OLLAMA_HOST:http://0.0.0.0:11434 OLLAMA_KEEP_ALIVE:5m0s OLLAMA_KV_CACHE_TYPE: OLLAMA_LLM_LIBRARY:vulkan OLLAMA_LOAD_TIMEOUT:5m0s OLLAMA_MAX_LOADED_MODELS:0 OLLAMA_MAX_QUEUE:512 OLLAMA_MODELS:/usr/share/ollama/.ollama/models OLLAMA_MULTIUSER_CACHE:false OLLAMA_NEW_ENGINE:false OLLAMA_NOHISTORY:false OLLAMA_NOPRUNE:false OLLAMA_NUM_PARALLEL:1 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://* vscode-webview://* vscode-file://*] OLLAMA_REMOTES:[ollama.com] OLLAMA_SCHED_SPREAD:false OLLAMA_VULKAN:true ROCR_VISIBLE_DEVICES: http_proxy: https_proxy: no_proxy:]"
Jan 11 20:00:02 ark ollama[4957]: time=2026-01-11T20:00:02.999-08:00 level=INFO source=images.go:493 msg="total blobs: 231"
Jan 11 20:00:03 ark ollama[4957]: time=2026-01-11T20:00:03.001-08:00 level=INFO source=images.go:500 msg="total unused blobs removed: 0"
Jan 11 20:00:03 ark ollama[4957]: time=2026-01-11T20:00:03.002-08:00 level=INFO source=routes.go:1607 msg="Listening on [::]:11434 (version 0.13.5)"
Jan 11 20:00:03 ark ollama[4957]: time=2026-01-11T20:00:03.002-08:00 level=INFO source=runner.go:67 msg="discovering available GPUs..."
Jan 11 20:00:03 ark ollama[4957]: time=2026-01-11T20:00:03.002-08:00 level=INFO source=server.go:429 msg="starting runner" cmd="/usr/local/bin/ollama runner --ollama-engine --port 40017"
Jan 11 20:00:03 ark ollama[4957]: time=2026-01-11T20:00:03.105-08:00 level=INFO source=types.go:42 msg="inference compute" id=00000000-c200-0000-0000-000000000000 filter_id="" library=Vulkan compute=0.0 name=Vulkan0 description="AMD Radeon Graphics (RADV GFX1151)" libdirs=ollama,vulkan driver=0.0 pci_id=0000:c2:00.0 type=iGPU total="61.9 GiB" available="61.4 GiB"

OS

Linux

GPU

AMD

CPU

AMD

Ollama version

0.13.5

Originally created by @na-g on GitHub (Jan 12, 2026). Original GitHub issue: https://github.com/ollama/ollama/issues/13681 ### What is the issue? I am running ` Ubuntu 25.10 (GNU/Linux 6.17.0-8-generic x86_64)`. According to `amd-ttm` I have a TTM page limit of 96GB. ``` $ amd-ttm 💻 Current TTM pages limit: 25165824 pages (96.00 GB) 💻 Total system memory: 122.84 GB ``` My ollama version is `0.13.5`. ``` $ ollama --version ollama version is 0.13.5 ``` The ROCm provider sees the 512MB allocated in the BIOS. The Vulkan provider sees 64 of the 96GB. I am happy to add whatever additional information may be helpful. ### Relevant log output ```shell Using no OLLAMA_LLM_LIBRARY $ sudo journalctl -fu ollama.service Jan 11 19:54:13 ark ollama[4493]: time=2026-01-11T19:54:13.479-08:00 level=INFO source=routes.go:1607 msg="Listening on [::]:11434 (version 0.13.5)" Jan 11 19:54:13 ark ollama[4493]: time=2026-01-11T19:54:13.481-08:00 level=INFO source=runner.go:67 msg="discovering available GPUs..." Jan 11 19:54:13 ark ollama[4493]: time=2026-01-11T19:54:13.483-08:00 level=INFO source=server.go:429 msg="starting runner" cmd="/usr/local/bin/ollama runner --ollama-engine --port 44333" Jan 11 19:54:13 ark ollama[4493]: time=2026-01-11T19:54:13.512-08:00 level=INFO source=server.go:429 msg="starting runner" cmd="/usr/local/bin/ollama runner --ollama-engine --port 34305" Jan 11 19:54:14 ark ollama[4493]: time=2026-01-11T19:54:14.714-08:00 level=INFO source=runner.go:106 msg="experimental Vulkan support disabled. To enable, set OLLAMA_VULKAN=1" Jan 11 19:54:14 ark ollama[4493]: time=2026-01-11T19:54:14.714-08:00 level=INFO source=server.go:429 msg="starting runner" cmd="/usr/local/bin/ollama runner --ollama-engine --port 37913" Jan 11 19:54:14 ark ollama[4493]: time=2026-01-11T19:54:14.733-08:00 level=INFO source=server.go:429 msg="starting runner" cmd="/usr/local/bin/ollama runner --ollama-engine --port 32935" Jan 11 19:54:15 ark ollama[4493]: time=2026-01-11T19:54:15.366-08:00 level=INFO source=types.go:42 msg="inference compute" id=0 filter_id=0 library=ROCm compute=gfx1151 name=ROCm0 description="AMD Radeon Graphics" libdirs=ollama,rocm driver=60342.13 pci_id=0000:c2:00.0 type=iGPU total="512.0 MiB" available="67.4 MiB" Jan 11 19:54:15 ark ollama[4493]: time=2026-01-11T19:54:15.366-08:00 level=INFO source=routes.go:1648 msg="entering low vram mode" "total vram"="512.0 MiB" threshold="20.0 GiB" Jan 11 19:56:17 ark ollama[4493]: [GIN] 2026/01/11 - 19:56:17 | 200 | 35.498192ms | 127.0.0.1 | GET "/api/version" ===================================================================================== Using OLLAMA_VULKAN=1 and OLLAMA_LLM_LIBRARY=vulkan $ sudo journalctl -fu ollama ... Jan 11 20:00:02 ark systemd[1]: Started ollama.service - Ollama Service. Jan 11 20:00:02 ark ollama[4957]: time=2026-01-11T20:00:02.993-08:00 level=INFO source=routes.go:1554 msg="server config" env="map[CUDA_VISIBLE_DEVICES: GGML_VK_VISIBLE_DEVICES: GPU_DEVICE_ORDINAL: HIP_VISIBLE_DEVICES: HSA_OVERRIDE_GFX_VERSION: HTTPS_PROXY: HTTP_PROXY: NO_PROXY: OLLAMA_CONTEXT_LENGTH:4096 OLLAMA_DEBUG:INFO OLLAMA_FLASH_ATTENTION:false OLLAMA_GPU_OVERHEAD:0 OLLAMA_HOST:http://0.0.0.0:11434 OLLAMA_KEEP_ALIVE:5m0s OLLAMA_KV_CACHE_TYPE: OLLAMA_LLM_LIBRARY:vulkan OLLAMA_LOAD_TIMEOUT:5m0s OLLAMA_MAX_LOADED_MODELS:0 OLLAMA_MAX_QUEUE:512 OLLAMA_MODELS:/usr/share/ollama/.ollama/models OLLAMA_MULTIUSER_CACHE:false OLLAMA_NEW_ENGINE:false OLLAMA_NOHISTORY:false OLLAMA_NOPRUNE:false OLLAMA_NUM_PARALLEL:1 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://* vscode-webview://* vscode-file://*] OLLAMA_REMOTES:[ollama.com] OLLAMA_SCHED_SPREAD:false OLLAMA_VULKAN:true ROCR_VISIBLE_DEVICES: http_proxy: https_proxy: no_proxy:]" Jan 11 20:00:02 ark ollama[4957]: time=2026-01-11T20:00:02.999-08:00 level=INFO source=images.go:493 msg="total blobs: 231" Jan 11 20:00:03 ark ollama[4957]: time=2026-01-11T20:00:03.001-08:00 level=INFO source=images.go:500 msg="total unused blobs removed: 0" Jan 11 20:00:03 ark ollama[4957]: time=2026-01-11T20:00:03.002-08:00 level=INFO source=routes.go:1607 msg="Listening on [::]:11434 (version 0.13.5)" Jan 11 20:00:03 ark ollama[4957]: time=2026-01-11T20:00:03.002-08:00 level=INFO source=runner.go:67 msg="discovering available GPUs..." Jan 11 20:00:03 ark ollama[4957]: time=2026-01-11T20:00:03.002-08:00 level=INFO source=server.go:429 msg="starting runner" cmd="/usr/local/bin/ollama runner --ollama-engine --port 40017" Jan 11 20:00:03 ark ollama[4957]: time=2026-01-11T20:00:03.105-08:00 level=INFO source=types.go:42 msg="inference compute" id=00000000-c200-0000-0000-000000000000 filter_id="" library=Vulkan compute=0.0 name=Vulkan0 description="AMD Radeon Graphics (RADV GFX1151)" libdirs=ollama,vulkan driver=0.0 pci_id=0000:c2:00.0 type=iGPU total="61.9 GiB" available="61.4 GiB" ``` ### OS Linux ### GPU AMD ### CPU AMD ### Ollama version 0.13.5
GiteaMirror added the bug label 2026-04-22 18:34:09 -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#34743
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?