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 #11348] ROCm GPU core dump with big enough context #33247

New Issue
Closed
opened 2026-04-22 15:45:14 -05:00 by GiteaMirror · 3 comments
GiteaMirror commented 2026-04-22 15:45:14 -05:00
Owner
Copy Link

Originally created by @FromCreator on GitHub (Jul 9, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/11348

What is the issue?

❯ ollama run gemma3:27b-it-qat
>>> hi
Hi there! How can I help you today? 

>>> write a poem
Error: model runner has unexpectedly stopped, this may be due to resource limitations or an internal error, check ollama server logs for details

The model runs for a bit before crashing after "write a poem." However, skipping the initial "hi" prompt and asking to immediately "write a poem" works as expected. Smaller models act similarly but allow more context length before gpu core dumping. Disable ROCm and the model works as expected.

Relevant log output

From the server logs:

GPU core dump created: gpucore.1512130
:0:rocdevice.cpp            :2991: 65291314601 us:  Callback: Queue 0x7f1f38200000 aborting with error : HSA_STATUS_ERROR_ILLEGAL_INSTRUCTION: The agent attempted to execute an illegal shader instruction. code: 0x2a
time=2025-07-09T15:19:41.196-04:00 level=ERROR source=server.go:807 msg="post predict" error="Post \"http://127.0.0.1:36769/completion\": EOF"

full server logs:

time=2025-07-09T15:15:39.709-04:00 level=INFO source=routes.go:1235 msg="server config" env="map[CUDA_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://127.0.0.1:11434 OLLAMA_INTEL_GPU:false OLLAMA_KEEP_ALIVE:5m0s OLLAMA_KV_CACHE_TYPE: OLLAMA_LLM_LIBRARY: OLLAMA_LOAD_TIMEOUT:5m0s OLLAMA_MAX_LOADED_MODELS:0 OLLAMA_MAX_QUEUE:512 OLLAMA_MODELS:/home/user/.ollama/models OLLAMA_MULTIUSER_CACHE:false OLLAMA_NEW_ENGINE:false 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://* vscode-webview://* vscode-file://*] OLLAMA_SCHED_SPREAD:false ROCR_VISIBLE_DEVICES: http_proxy: https_proxy: no_proxy:]"
time=2025-07-09T15:15:39.710-04:00 level=INFO source=images.go:476 msg="total blobs: 12"
time=2025-07-09T15:15:39.710-04:00 level=INFO source=images.go:483 msg="total unused blobs removed: 0"
time=2025-07-09T15:15:39.710-04:00 level=INFO source=routes.go:1288 msg="Listening on 127.0.0.1:11434 (version 0.9.5)"
time=2025-07-09T15:15:39.711-04:00 level=INFO source=gpu.go:217 msg="looking for compatible GPUs"
time=2025-07-09T15:15:39.751-04:00 level=WARN source=amd_linux.go:61 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=2025-07-09T15:15:39.751-04:00 level=INFO source=amd_linux.go:386 msg="amdgpu is supported" gpu=GPU-b65c57500c6cdb4d gpu_type=gfx1030
time=2025-07-09T15:15:39.751-04:00 level=INFO source=types.go:130 msg="inference compute" id=GPU-b65c57500c6cdb4d library=rocm variant="" compute=gfx1030 driver=0.0 name=1002:73bf total="16.0 GiB" available="15.1 GiB"
[GIN] 2025/07/09 - 15:15:46 | 200 |       43.09µs |       127.0.0.1 | HEAD     "/"
[GIN] 2025/07/09 - 15:15:46 | 200 |   57.844066ms |       127.0.0.1 | POST     "/api/show"
time=2025-07-09T15:15:46.355-04:00 level=INFO source=server.go:135 msg="system memory" total="62.6 GiB" free="58.6 GiB" free_swap="8.2 GiB"
time=2025-07-09T15:15:46.356-04:00 level=INFO source=server.go:175 msg=offload library=rocm layers.requested=-1 layers.model=63 layers.offload=55 layers.split="" memory.available="[15.1 GiB]" memory.gpu_overhead="0 B" memory.required.full="21.0 GiB" memory.required.partial="15.0 GiB" memory.required.kv="944.0 MiB" memory.required.allocations="[15.0 GiB]" memory.weights.total="16.0 GiB" memory.weights.repeating="13.4 GiB" memory.weights.nonrepeating="2.6 GiB" memory.graph.full="522.5 MiB" memory.graph.partial="1.6 GiB" projector.weights="806.2 MiB" projector.graph="1.0 GiB"
time=2025-07-09T15:15:46.380-04:00 level=INFO source=server.go:438 msg="starting llama server" cmd="/usr/bin/ollama runner --ollama-engine --model /home/user/.ollama/models/blobs/sha256-ccc0cddac56136ef0969cf2e3e9ac051124c937be42503b47ec570dead85ff87 --ctx-size 4096 --batch-size 512 --n-gpu-layers 55 --threads 6 --parallel 1 --port 36769"
time=2025-07-09T15:15:46.381-04:00 level=INFO source=sched.go:483 msg="loaded runners" count=1
time=2025-07-09T15:15:46.381-04:00 level=INFO source=server.go:598 msg="waiting for llama runner to start responding"
time=2025-07-09T15:15:46.381-04:00 level=INFO source=server.go:632 msg="waiting for server to become available" status="llm server not responding"
time=2025-07-09T15:15:46.389-04:00 level=INFO source=runner.go:925 msg="starting ollama engine"
time=2025-07-09T15:15:46.389-04:00 level=INFO source=runner.go:983 msg="Server listening on 127.0.0.1:36769"
time=2025-07-09T15:15:46.410-04:00 level=INFO source=ggml.go:92 msg="" architecture=gemma3 file_type=Q4_0 name="" description="" num_tensors=1247 num_key_values=40
time=2025-07-09T15:15:46.632-04:00 level=INFO source=server.go:632 msg="waiting for server to become available" status="llm server loading model"
ggml_cuda_init: GGML_CUDA_FORCE_MMQ:    no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 1 ROCm devices:
  Device 0: AMD Radeon RX 6800 XT, gfx1030 (0x1030), VMM: no, Wave Size: 32
load_backend: loaded ROCm backend from /usr/lib/ollama/libggml-hip.so
load_backend: loaded CPU backend from /usr/lib/ollama/libggml-cpu-alderlake.so
time=2025-07-09T15:15:48.395-04:00 level=INFO source=ggml.go:104 msg=system CPU.0.SSE3=1 CPU.0.SSSE3=1 CPU.0.AVX=1 CPU.0.AVX_VNNI=1 CPU.0.AVX2=1 CPU.0.F16C=1 CPU.0.FMA=1 CPU.0.BMI2=1 CPU.0.LLAMAFILE=1 CPU.1.LLAMAFILE=1 ROCm.0.NO_VMM=1 ROCm.0.PEER_MAX_BATCH_SIZE=128 compiler=cgo(gcc)
time=2025-07-09T15:15:48.603-04:00 level=INFO source=ggml.go:362 msg="model weights" buffer=CPU size="7.6 GiB"
time=2025-07-09T15:15:48.603-04:00 level=INFO source=ggml.go:362 msg="model weights" buffer=ROCm0 size="11.9 GiB"
time=2025-07-09T15:15:48.721-04:00 level=INFO source=ggml.go:651 msg="compute graph" backend=ROCm0 buffer_type=ROCm0 size="0 B"
time=2025-07-09T15:15:48.721-04:00 level=INFO source=ggml.go:651 msg="compute graph" backend=CPU buffer_type=CPU size="1.1 GiB"
time=2025-07-09T15:15:48.749-04:00 level=INFO source=ggml.go:651 msg="compute graph" backend=ROCm0 buffer_type=ROCm0 size="288.0 MiB"
time=2025-07-09T15:15:48.749-04:00 level=INFO source=ggml.go:651 msg="compute graph" backend=CPU buffer_type=CPU size="1.1 GiB"
time=2025-07-09T15:15:50.400-04:00 level=INFO source=server.go:637 msg="llama runner started in 4.02 seconds"
[GIN] 2025/07/09 - 15:15:50 | 200 |  4.120390524s |       127.0.0.1 | POST     "/api/generate"
[GIN] 2025/07/09 - 15:17:40 | 200 |   2.72379499s |       127.0.0.1 | POST     "/api/chat"
GPU core dump created: gpucore.1512130
:0:rocdevice.cpp            :2991: 65291314601 us:  Callback: Queue 0x7f1f38200000 aborting with error : HSA_STATUS_ERROR_ILLEGAL_INSTRUCTION: The agent attempted to execute an illegal shader instruction. code: 0x2a
time=2025-07-09T15:19:41.196-04:00 level=ERROR source=server.go:807 msg="post predict" error="Post \"http://127.0.0.1:36769/completion\": EOF"
[GIN] 2025/07/09 - 15:19:41 | 200 |         1m51s |       127.0.0.1 | POST     "/api/chat"

OS

EndeavourOS x86_64
Kernel: Linux 6.15.5-arch1-1

GPU

AMD 6800XT

CPU

12th Gen Intel(R) Core(TM) i5-12600K (16) @ 4z

Ollama version

ollama: 0.9.5 (yes I know 0.9.6 was just released but it isn't in the arch repos yet, will give an update when it's available)
ollama-rocm: 0.9.5

Originally created by @FromCreator on GitHub (Jul 9, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/11348 ### What is the issue? ``` ❯ ollama run gemma3:27b-it-qat >>> hi Hi there! How can I help you today? >>> write a poem Error: model runner has unexpectedly stopped, this may be due to resource limitations or an internal error, check ollama server logs for details ``` The model runs for a bit before crashing after "write a poem." However, skipping the initial "hi" prompt and asking to immediately "write a poem" works as expected. Smaller models act similarly but allow more context length before gpu core dumping. Disable ROCm and the model works as expected. ### Relevant log output From the server logs: ```shell GPU core dump created: gpucore.1512130 :0:rocdevice.cpp :2991: 65291314601 us: Callback: Queue 0x7f1f38200000 aborting with error : HSA_STATUS_ERROR_ILLEGAL_INSTRUCTION: The agent attempted to execute an illegal shader instruction. code: 0x2a time=2025-07-09T15:19:41.196-04:00 level=ERROR source=server.go:807 msg="post predict" error="Post \"http://127.0.0.1:36769/completion\": EOF" ``` full server logs: ```shell time=2025-07-09T15:15:39.709-04:00 level=INFO source=routes.go:1235 msg="server config" env="map[CUDA_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://127.0.0.1:11434 OLLAMA_INTEL_GPU:false OLLAMA_KEEP_ALIVE:5m0s OLLAMA_KV_CACHE_TYPE: OLLAMA_LLM_LIBRARY: OLLAMA_LOAD_TIMEOUT:5m0s OLLAMA_MAX_LOADED_MODELS:0 OLLAMA_MAX_QUEUE:512 OLLAMA_MODELS:/home/user/.ollama/models OLLAMA_MULTIUSER_CACHE:false OLLAMA_NEW_ENGINE:false 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://* vscode-webview://* vscode-file://*] OLLAMA_SCHED_SPREAD:false ROCR_VISIBLE_DEVICES: http_proxy: https_proxy: no_proxy:]" time=2025-07-09T15:15:39.710-04:00 level=INFO source=images.go:476 msg="total blobs: 12" time=2025-07-09T15:15:39.710-04:00 level=INFO source=images.go:483 msg="total unused blobs removed: 0" time=2025-07-09T15:15:39.710-04:00 level=INFO source=routes.go:1288 msg="Listening on 127.0.0.1:11434 (version 0.9.5)" time=2025-07-09T15:15:39.711-04:00 level=INFO source=gpu.go:217 msg="looking for compatible GPUs" time=2025-07-09T15:15:39.751-04:00 level=WARN source=amd_linux.go:61 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=2025-07-09T15:15:39.751-04:00 level=INFO source=amd_linux.go:386 msg="amdgpu is supported" gpu=GPU-b65c57500c6cdb4d gpu_type=gfx1030 time=2025-07-09T15:15:39.751-04:00 level=INFO source=types.go:130 msg="inference compute" id=GPU-b65c57500c6cdb4d library=rocm variant="" compute=gfx1030 driver=0.0 name=1002:73bf total="16.0 GiB" available="15.1 GiB" [GIN] 2025/07/09 - 15:15:46 | 200 | 43.09µs | 127.0.0.1 | HEAD "/" [GIN] 2025/07/09 - 15:15:46 | 200 | 57.844066ms | 127.0.0.1 | POST "/api/show" time=2025-07-09T15:15:46.355-04:00 level=INFO source=server.go:135 msg="system memory" total="62.6 GiB" free="58.6 GiB" free_swap="8.2 GiB" time=2025-07-09T15:15:46.356-04:00 level=INFO source=server.go:175 msg=offload library=rocm layers.requested=-1 layers.model=63 layers.offload=55 layers.split="" memory.available="[15.1 GiB]" memory.gpu_overhead="0 B" memory.required.full="21.0 GiB" memory.required.partial="15.0 GiB" memory.required.kv="944.0 MiB" memory.required.allocations="[15.0 GiB]" memory.weights.total="16.0 GiB" memory.weights.repeating="13.4 GiB" memory.weights.nonrepeating="2.6 GiB" memory.graph.full="522.5 MiB" memory.graph.partial="1.6 GiB" projector.weights="806.2 MiB" projector.graph="1.0 GiB" time=2025-07-09T15:15:46.380-04:00 level=INFO source=server.go:438 msg="starting llama server" cmd="/usr/bin/ollama runner --ollama-engine --model /home/user/.ollama/models/blobs/sha256-ccc0cddac56136ef0969cf2e3e9ac051124c937be42503b47ec570dead85ff87 --ctx-size 4096 --batch-size 512 --n-gpu-layers 55 --threads 6 --parallel 1 --port 36769" time=2025-07-09T15:15:46.381-04:00 level=INFO source=sched.go:483 msg="loaded runners" count=1 time=2025-07-09T15:15:46.381-04:00 level=INFO source=server.go:598 msg="waiting for llama runner to start responding" time=2025-07-09T15:15:46.381-04:00 level=INFO source=server.go:632 msg="waiting for server to become available" status="llm server not responding" time=2025-07-09T15:15:46.389-04:00 level=INFO source=runner.go:925 msg="starting ollama engine" time=2025-07-09T15:15:46.389-04:00 level=INFO source=runner.go:983 msg="Server listening on 127.0.0.1:36769" time=2025-07-09T15:15:46.410-04:00 level=INFO source=ggml.go:92 msg="" architecture=gemma3 file_type=Q4_0 name="" description="" num_tensors=1247 num_key_values=40 time=2025-07-09T15:15:46.632-04:00 level=INFO source=server.go:632 msg="waiting for server to become available" status="llm server loading model" ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no ggml_cuda_init: found 1 ROCm devices: Device 0: AMD Radeon RX 6800 XT, gfx1030 (0x1030), VMM: no, Wave Size: 32 load_backend: loaded ROCm backend from /usr/lib/ollama/libggml-hip.so load_backend: loaded CPU backend from /usr/lib/ollama/libggml-cpu-alderlake.so time=2025-07-09T15:15:48.395-04:00 level=INFO source=ggml.go:104 msg=system CPU.0.SSE3=1 CPU.0.SSSE3=1 CPU.0.AVX=1 CPU.0.AVX_VNNI=1 CPU.0.AVX2=1 CPU.0.F16C=1 CPU.0.FMA=1 CPU.0.BMI2=1 CPU.0.LLAMAFILE=1 CPU.1.LLAMAFILE=1 ROCm.0.NO_VMM=1 ROCm.0.PEER_MAX_BATCH_SIZE=128 compiler=cgo(gcc) time=2025-07-09T15:15:48.603-04:00 level=INFO source=ggml.go:362 msg="model weights" buffer=CPU size="7.6 GiB" time=2025-07-09T15:15:48.603-04:00 level=INFO source=ggml.go:362 msg="model weights" buffer=ROCm0 size="11.9 GiB" time=2025-07-09T15:15:48.721-04:00 level=INFO source=ggml.go:651 msg="compute graph" backend=ROCm0 buffer_type=ROCm0 size="0 B" time=2025-07-09T15:15:48.721-04:00 level=INFO source=ggml.go:651 msg="compute graph" backend=CPU buffer_type=CPU size="1.1 GiB" time=2025-07-09T15:15:48.749-04:00 level=INFO source=ggml.go:651 msg="compute graph" backend=ROCm0 buffer_type=ROCm0 size="288.0 MiB" time=2025-07-09T15:15:48.749-04:00 level=INFO source=ggml.go:651 msg="compute graph" backend=CPU buffer_type=CPU size="1.1 GiB" time=2025-07-09T15:15:50.400-04:00 level=INFO source=server.go:637 msg="llama runner started in 4.02 seconds" [GIN] 2025/07/09 - 15:15:50 | 200 | 4.120390524s | 127.0.0.1 | POST "/api/generate" [GIN] 2025/07/09 - 15:17:40 | 200 | 2.72379499s | 127.0.0.1 | POST "/api/chat" GPU core dump created: gpucore.1512130 :0:rocdevice.cpp :2991: 65291314601 us: Callback: Queue 0x7f1f38200000 aborting with error : HSA_STATUS_ERROR_ILLEGAL_INSTRUCTION: The agent attempted to execute an illegal shader instruction. code: 0x2a time=2025-07-09T15:19:41.196-04:00 level=ERROR source=server.go:807 msg="post predict" error="Post \"http://127.0.0.1:36769/completion\": EOF" [GIN] 2025/07/09 - 15:19:41 | 200 | 1m51s | 127.0.0.1 | POST "/api/chat" ``` ### OS EndeavourOS x86_64 Kernel: Linux 6.15.5-arch1-1 ### GPU AMD 6800XT ### CPU 12th Gen Intel(R) Core(TM) i5-12600K (16) @ 4z ### Ollama version ollama: 0.9.5 (yes I know 0.9.6 was just released but it isn't in the arch repos yet, will give an update when it's available) ollama-rocm: 0.9.5
GiteaMirror added the bug label 2026-04-22 15:45:14 -05:00
GiteaMirror commented 2026-04-22 15:45:35 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Jul 9, 2025):

What's the output of rocm-smi -a?

<!-- gh-comment-id:3053828493 --> @rick-github commented on GitHub (Jul 9, 2025): What's the output of `rocm-smi -a`?
GiteaMirror commented 2026-04-22 15:45:36 -05:00
Author
Owner
Copy Link

@FromCreator commented on GitHub (Jul 10, 2025):

rocm-smi -a

============================ ROCm System Management Interface ============================
============================== Version of System Component ===============================
Driver version: 6.15.5-arch1-1
==========================================================================================
=========================================== ID ===========================================
GPU[0]		: Device Name: 		AMD Radeon RX 6800 XT
GPU[0]		: Device ID: 		0x73bf
GPU[0]		: Device Rev: 		0xc1
GPU[0]		: Subsystem ID: 	0x2328
GPU[0]		: GUID: 		27684
==========================================================================================
======================================= Unique ID ========================================
GPU[0]		: Unique ID: 0xb65c57500c6cdb4d
==========================================================================================
========================================= VBIOS ==========================================
GPU[0]		: VBIOS version: 113-D412-R68XTGOL
==========================================================================================
====================================== Temperature =======================================
GPU[0]		: Temperature (Sensor edge) (C): 55.0
GPU[0]		: Temperature (Sensor junction) (C): 57.0
GPU[0]		: Temperature (Sensor memory) (C): 62.0
==========================================================================================
=============================== Current clock frequencies ================================
GPU[0]		: dcefclk clock level: 1: (960Mhz)
GPU[0]		: fclk clock level: 1: (1276Mhz)
GPU[0]		: mclk clock level: 3: (1000Mhz)
GPU[0]		: sclk clock level: 0: (500Mhz)
GPU[0]		: socclk clock level: 1: (800Mhz)
GPU[0]		: pcie clock level: 0 (16.0GT/s x8)
==========================================================================================
=================================== Current Fan Metric ===================================
GPU[0]		: Fan Level: 83 (33%)
GPU[0]		: Fan RPM: 934
==========================================================================================
================================= Show Performance Level =================================
GPU[0]		: Performance Level: auto
==========================================================================================
==================================== OverDrive Level =====================================
GPU[0]		: get_overdrive_level_sclk, Not supported on the given system
==========================================================================================
==================================== OverDrive Level =====================================
GPU[0]		: get_mem_overdrive_level_mclk, Not supported on the given system
==========================================================================================
======================================= Power Cap ========================================
GPU[0]		: Max Graphics Package Power (W): 264.0
==========================================================================================
================================== Show Power Profiles ===================================
GPU[0]		: 1. Available power profile (#1 of 7): CUSTOM
GPU[0]		: 2. Available power profile (#2 of 7): VIDEO
GPU[0]		: 3. Available power profile (#3 of 7): POWER SAVING
GPU[0]		: 4. Available power profile (#4 of 7): COMPUTE
GPU[0]		: 5. Available power profile (#5 of 7): VR
GPU[0]		: 6. Available power profile (#6 of 7): 3D FULL SCREEN
GPU[0]		: 7. Available power profile (#7 of 7): BOOTUP DEFAULT*
==========================================================================================
=================================== Power Consumption ====================================
GPU[0]		: Average Graphics Package Power (W): 49.0
==========================================================================================
============================== Supported clock frequencies ===============================
GPU[0]		: Supported dcefclk frequencies on GPU0
GPU[0]		: 0: 417Mhz
GPU[0]		: 1: 960Mhz *
GPU[0]		: 2: 1200Mhz
GPU[0]		: 
GPU[0]		: Supported fclk frequencies on GPU0
GPU[0]		: 0: 500Mhz
GPU[0]		: 1: 1276Mhz *
GPU[0]		: 2: 1941Mhz
GPU[0]		: 
GPU[0]		: Supported mclk frequencies on GPU0
GPU[0]		: 0: 96Mhz
GPU[0]		: 1: 456Mhz
GPU[0]		: 2: 673Mhz
GPU[0]		: 3: 1000Mhz *
GPU[0]		: 
GPU[0]		: Supported sclk frequencies on GPU0
GPU[0]		: 0: 500Mhz *
GPU[0]		: 1: 2575Mhz
GPU[0]		: 
GPU[0]		: Supported socclk frequencies on GPU0
GPU[0]		: 0: 480Mhz
GPU[0]		: 1: 800Mhz *
GPU[0]		: 2: 1200Mhz
GPU[0]		: 
GPU[0]		: Supported PCIe frequencies on GPU0
GPU[0]		: 0: 16.0GT/s x8 *
GPU[0]		: 1: 16.0GT/s x8
GPU[0]		: 
------------------------------------------------------------------------------------------
==========================================================================================
=================================== % time GPU is busy ===================================
GPU[0]		: GPU use (%): 7
==========================================================================================
=================================== Current Memory Use ===================================
GPU[0]		: GPU Memory Allocated (VRAM%): 7
GPU[0]		: GPU Memory Read/Write Activity (%): 1
GPU[0]		: Memory Activity: N/A
GPU[0]		: Avg. Memory Bandwidth: 0
==========================================================================================
===================================== Memory Vendor ======================================
GPU[0]		: GPU memory vendor: micron
==========================================================================================
================================== PCIe Replay Counter ===================================
GPU[0]		: PCIe Replay Count: 0
==========================================================================================
===================================== Serial Number ======================================
GPU[0]		: get_serial_number, Not supported on the given system
GPU[0]		: Serial Number: N/A
==========================================================================================
===================================== KFD Processes ======================================
No KFD PIDs currently running
==========================================================================================
================================== GPUs Indexed by PID ===================================
No KFD PIDs currently running
==========================================================================================
======================= GPU Memory clock frequencies and voltages ========================
GPU[0]		: OD_SCLK:
GPU[0]		: 0: 500Mhz
GPU[0]		: 1: 2449Mhz
GPU[0]		: OD_MCLK:
GPU[0]		: 0: 97Mhz
GPU[0]		: 1: 1000Mhz
==========================================================================================
==================================== Current voltage =====================================
GPU[0]		: Voltage (mV): 856
==========================================================================================
======================================= PCI Bus ID =======================================
GPU[0]		: PCI Bus: 0000:04:00.0
==========================================================================================
================================== Firmware Information ==================================
GPU[0]		: ASD firmware version: 	0x210000ef
GPU[0]		: CE firmware version: 		37
GPU[0]		: ME firmware version: 		64
GPU[0]		: MEC firmware version: 	131
GPU[0]		: MEC2 firmware version: 	131
GPU[0]		: PFP firmware version: 	109
GPU[0]		: RLC firmware version: 	96
GPU[0]		: SDMA firmware version: 	85
GPU[0]		: SDMA2 firmware version: 	85
GPU[0]		: SMC firmware version: 	00.58.90.00
GPU[0]		: SOS firmware version: 	0x00210f64
GPU[0]		: TA RAS firmware version: 	27.00.01.62
GPU[0]		: TA XGMI firmware version: 	32.00.00.20
GPU[0]		: VCN firmware version: 	0x04121008
==========================================================================================
====================================== Product Info ======================================
GPU[0]		: Card Series: 		AMD Radeon RX 6800 XT
GPU[0]		: Card Model: 		0x73bf
GPU[0]		: Card Vendor: 		Advanced Micro Devices, Inc. [AMD/ATI]
GPU[0]		: Card SKU: 		D412
GPU[0]		: Subsystem ID: 	0x2328
GPU[0]		: Device Rev: 		0xc1
GPU[0]		: Node ID: 		1
GPU[0]		: GUID: 		27684
GPU[0]		: GFX Version: 		gfx1030
==========================================================================================
======================================= Pages Info =======================================
GPU[0]		: ras, Not supported on the given system
================================= Show Valid sclk Range ==================================
GPU[0]		: Valid sclk range: 500Mhz - 2449Mhz
==========================================================================================
================================= Show Valid mclk Range ==================================
GPU[0]		: Valid mclk range: 97Mhz - 1000Mhz
==========================================================================================
================================ Show Valid voltage Range ================================
WARNING: GPU[0]	: Voltage curve regions unsupported.
==========================================================================================
================================== Voltage Curve Points ==================================
WARNING: GPU[0]	: Voltage curve Points unsupported.
==========================================================================================
==================================== Consumed Energy =====================================
GPU[0]		: Energy counter: 3095321488
GPU[0]		: Accumulated Energy (uJ): 47358419356.79
==========================================================================================
=============================== Current Compute Partition ================================
GPU[0]		: Not supported on the given system
==========================================================================================
================================ Current Memory Partition ================================
GPU[0]		: Not supported on the given system
==========================================================================================
====================================== GPU Metrics =======================================
GPU[0]		: Metric Version and Size (Bytes): 1.3 120
GPU[0]		: temperature_edge (C): 55
GPU[0]		: temperature_hotspot (C): 58
GPU[0]		: temperature_mem (C): 62
GPU[0]		: temperature_vrgfx (C): 57
GPU[0]		: temperature_vrsoc (C): 58
GPU[0]		: temperature_vrmem (C): 60
GPU[0]		: average_gfx_activity (%): 5
GPU[0]		: average_umc_activity (%): 1
GPU[0]		: average_mm_activity (%): 0
GPU[0]		: average_socket_power (W): 49
GPU[0]		: energy_accumulator (15.259uJ (2^-16)): 3095321537
GPU[0]		: system_clock_counter (ns): 82187791116982
GPU[0]		: average_gfxclk_frequency (MHz): 36
GPU[0]		: average_socclk_frequency (MHz): N/A
GPU[0]		: average_uclk_frequency (MHz): 990
GPU[0]		: average_vclk0_frequency (MHz): 33
GPU[0]		: average_dclk0_frequency (MHz): 33
GPU[0]		: average_vclk1_frequency (MHz): 33
GPU[0]		: average_dclk1_frequency (MHz): 33
GPU[0]		: current_gfxclk (MHz): 500
GPU[0]		: current_socclk (MHz): 800
GPU[0]		: current_uclk (MHz): 1000
GPU[0]		: current_vclk0 (MHz): 0
GPU[0]		: current_dclk0 (MHz): 0
GPU[0]		: current_vclk1 (MHz): 0
GPU[0]		: current_dclk1 (MHz): 0
GPU[0]		: throttle_status: 0
GPU[0]		: current_fan_speed (rpm): 934
GPU[0]		: pcie_link_width (Lanes): 8
GPU[0]		: pcie_link_speed (0.1 GT/s): 160
GPU[0]		: gfx_activity_acc (%): N/A
GPU[0]		: mem_activity_acc (%): N/A
GPU[0]		: temperature_hbm (C): ['N/A', 'N/A', 'N/A', 'N/A']
GPU[0]		: firmware_timestamp (10ns resolution): 18446744073709551606
GPU[0]		: voltage_soc (mV): 943
GPU[0]		: voltage_gfx (mV): 881
GPU[0]		: voltage_mem (mV): 1356
GPU[0]		: indep_throttle_status: 0
GPU[0]		: current_socket_power (W): N/A
GPU[0]		: vcn_activity (%): [0, 'N/A', 'N/A', 'N/A']
GPU[0]		: gfxclk_lock_status: N/A
GPU[0]		: xgmi_link_width: N/A
GPU[0]		: xgmi_link_speed (Gbps): N/A
GPU[0]		: pcie_bandwidth_acc (GB/s): N/A
GPU[0]		: pcie_bandwidth_inst (GB/s): N/A
GPU[0]		: pcie_l0_to_recov_count_acc (Count): N/A
GPU[0]		: pcie_replay_count_acc (Count): N/A
GPU[0]		: pcie_replay_rover_count_acc (Count): N/A
GPU[0]		: xgmi_read_data_acc (kB): ['N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A']
GPU[0]		: xgmi_write_data_acc (kB): ['N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A']
GPU[0]		: current_gfxclks (MHz): [500, 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A']
GPU[0]		: current_socclks (MHz): [800, 'N/A', 'N/A', 'N/A']
GPU[0]		: current_vclk0s (MHz): [0, 'N/A', 'N/A', 'N/A']
GPU[0]		: current_dclk0s (MHz): [0, 'N/A', 'N/A', 'N/A']
GPU[0]		: jpeg_activity (%): ['N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A']
GPU[0]		: pcie_nak_sent_count_acc (Count): N/A
GPU[0]		: pcie_nak_rcvd_count_acc (Count): N/A
GPU[0]		: accumulation_counter (Count): N/A
GPU[0]		: prochot_residency_acc (Count): N/A
GPU[0]		: ppt_residency_acc (Count): N/A
GPU[0]		: socket_thm_residency_acc (Count): N/A
GPU[0]		: vr_thm_residency_acc (Count): N/A
GPU[0]		: hbm_thm_residency_acc (Count): N/A
GPU[0]		: pcie_lc_perf_other_end_recovery (Count): N/A
GPU[0]		: vram_max_bandwidth (GB/s): N/A
GPU[0]		: xgmi_link_status (Up/Down): ['N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A']
GPU[0]		: num_partition: N/A
GPU[0] XCP[0]	: xcp_stats.gfx_busy_inst (%): ['N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A']
GPU[0] XCP[1]	: xcp_stats.gfx_busy_inst (%): ['N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A']
GPU[0] XCP[2]	: xcp_stats.gfx_busy_inst (%): ['N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A']
GPU[0] XCP[3]	: xcp_stats.gfx_busy_inst (%): ['N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A']
GPU[0] XCP[4]	: xcp_stats.gfx_busy_inst (%): ['N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A']
GPU[0] XCP[5]	: xcp_stats.gfx_busy_inst (%): ['N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A']
GPU[0] XCP[6]	: xcp_stats.gfx_busy_inst (%): ['N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A']
GPU[0] XCP[7]	: xcp_stats.gfx_busy_inst (%): ['N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A']
GPU[0] XCP[0]	: xcp_stats.jpeg_busy (%): ['N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A']
GPU[0] XCP[1]	: xcp_stats.jpeg_busy (%): ['N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A']
GPU[0] XCP[2]	: xcp_stats.jpeg_busy (%): ['N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A']
GPU[0] XCP[3]	: xcp_stats.jpeg_busy (%): ['N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A']
GPU[0] XCP[4]	: xcp_stats.jpeg_busy (%): ['N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A']
GPU[0] XCP[5]	: xcp_stats.jpeg_busy (%): ['N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A']
GPU[0] XCP[6]	: xcp_stats.jpeg_busy (%): ['N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A']
GPU[0] XCP[7]	: xcp_stats.jpeg_busy (%): ['N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A']
GPU[0] XCP[0]	: xcp_stats.vcn_busy (%): [0, 'N/A', 'N/A', 'N/A']
GPU[0] XCP[1]	: xcp_stats.vcn_busy (%): ['N/A', 'N/A', 'N/A', 'N/A']
GPU[0] XCP[2]	: xcp_stats.vcn_busy (%): ['N/A', 'N/A', 'N/A', 'N/A']
GPU[0] XCP[3]	: xcp_stats.vcn_busy (%): ['N/A', 'N/A', 'N/A', 'N/A']
GPU[0] XCP[4]	: xcp_stats.vcn_busy (%): ['N/A', 'N/A', 'N/A', 'N/A']
GPU[0] XCP[5]	: xcp_stats.vcn_busy (%): ['N/A', 'N/A', 'N/A', 'N/A']
GPU[0] XCP[6]	: xcp_stats.vcn_busy (%): ['N/A', 'N/A', 'N/A', 'N/A']
GPU[0] XCP[7]	: xcp_stats.vcn_busy (%): ['N/A', 'N/A', 'N/A', 'N/A']
GPU[0] XCP[0]	: xcp_stats.gfx_busy_acc (Count): ['N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A']
GPU[0] XCP[1]	: xcp_stats.gfx_busy_acc (Count): ['N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A']
GPU[0] XCP[2]	: xcp_stats.gfx_busy_acc (Count): ['N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A']
GPU[0] XCP[3]	: xcp_stats.gfx_busy_acc (Count): ['N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A']
GPU[0] XCP[4]	: xcp_stats.gfx_busy_acc (Count): ['N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A']
GPU[0] XCP[5]	: xcp_stats.gfx_busy_acc (Count): ['N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A']
GPU[0] XCP[6]	: xcp_stats.gfx_busy_acc (Count): ['N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A']
GPU[0] XCP[7]	: xcp_stats.gfx_busy_acc (Count): ['N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A']
GPU[0] XCP[0]	: xcp_stats.gfx_below_host_limit_acc (%): ['N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A']
GPU[0] XCP[1]	: xcp_stats.gfx_below_host_limit_acc (%): ['N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A']
GPU[0] XCP[2]	: xcp_stats.gfx_below_host_limit_acc (%): ['N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A']
GPU[0] XCP[3]	: xcp_stats.gfx_below_host_limit_acc (%): ['N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A']
GPU[0] XCP[4]	: xcp_stats.gfx_below_host_limit_acc (%): ['N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A']
GPU[0] XCP[5]	: xcp_stats.gfx_below_host_limit_acc (%): ['N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A']
GPU[0] XCP[6]	: xcp_stats.gfx_below_host_limit_acc (%): ['N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A']
GPU[0] XCP[7]	: xcp_stats.gfx_below_host_limit_acc (%): ['N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A']
==========================================================================================
================================== End of ROCm SMI Log ===================================
<!-- gh-comment-id:3054500741 --> @FromCreator commented on GitHub (Jul 10, 2025): `rocm-smi -a` ``` ============================ ROCm System Management Interface ============================ ============================== Version of System Component =============================== Driver version: 6.15.5-arch1-1 ========================================================================================== =========================================== ID =========================================== GPU[0] : Device Name: AMD Radeon RX 6800 XT GPU[0] : Device ID: 0x73bf GPU[0] : Device Rev: 0xc1 GPU[0] : Subsystem ID: 0x2328 GPU[0] : GUID: 27684 ========================================================================================== ======================================= Unique ID ======================================== GPU[0] : Unique ID: 0xb65c57500c6cdb4d ========================================================================================== ========================================= VBIOS ========================================== GPU[0] : VBIOS version: 113-D412-R68XTGOL ========================================================================================== ====================================== Temperature ======================================= GPU[0] : Temperature (Sensor edge) (C): 55.0 GPU[0] : Temperature (Sensor junction) (C): 57.0 GPU[0] : Temperature (Sensor memory) (C): 62.0 ========================================================================================== =============================== Current clock frequencies ================================ GPU[0] : dcefclk clock level: 1: (960Mhz) GPU[0] : fclk clock level: 1: (1276Mhz) GPU[0] : mclk clock level: 3: (1000Mhz) GPU[0] : sclk clock level: 0: (500Mhz) GPU[0] : socclk clock level: 1: (800Mhz) GPU[0] : pcie clock level: 0 (16.0GT/s x8) ========================================================================================== =================================== Current Fan Metric =================================== GPU[0] : Fan Level: 83 (33%) GPU[0] : Fan RPM: 934 ========================================================================================== ================================= Show Performance Level ================================= GPU[0] : Performance Level: auto ========================================================================================== ==================================== OverDrive Level ===================================== GPU[0] : get_overdrive_level_sclk, Not supported on the given system ========================================================================================== ==================================== OverDrive Level ===================================== GPU[0] : get_mem_overdrive_level_mclk, Not supported on the given system ========================================================================================== ======================================= Power Cap ======================================== GPU[0] : Max Graphics Package Power (W): 264.0 ========================================================================================== ================================== Show Power Profiles =================================== GPU[0] : 1. Available power profile (#1 of 7): CUSTOM GPU[0] : 2. Available power profile (#2 of 7): VIDEO GPU[0] : 3. Available power profile (#3 of 7): POWER SAVING GPU[0] : 4. Available power profile (#4 of 7): COMPUTE GPU[0] : 5. Available power profile (#5 of 7): VR GPU[0] : 6. Available power profile (#6 of 7): 3D FULL SCREEN GPU[0] : 7. Available power profile (#7 of 7): BOOTUP DEFAULT* ========================================================================================== =================================== Power Consumption ==================================== GPU[0] : Average Graphics Package Power (W): 49.0 ========================================================================================== ============================== Supported clock frequencies =============================== GPU[0] : Supported dcefclk frequencies on GPU0 GPU[0] : 0: 417Mhz GPU[0] : 1: 960Mhz * GPU[0] : 2: 1200Mhz GPU[0] : GPU[0] : Supported fclk frequencies on GPU0 GPU[0] : 0: 500Mhz GPU[0] : 1: 1276Mhz * GPU[0] : 2: 1941Mhz GPU[0] : GPU[0] : Supported mclk frequencies on GPU0 GPU[0] : 0: 96Mhz GPU[0] : 1: 456Mhz GPU[0] : 2: 673Mhz GPU[0] : 3: 1000Mhz * GPU[0] : GPU[0] : Supported sclk frequencies on GPU0 GPU[0] : 0: 500Mhz * GPU[0] : 1: 2575Mhz GPU[0] : GPU[0] : Supported socclk frequencies on GPU0 GPU[0] : 0: 480Mhz GPU[0] : 1: 800Mhz * GPU[0] : 2: 1200Mhz GPU[0] : GPU[0] : Supported PCIe frequencies on GPU0 GPU[0] : 0: 16.0GT/s x8 * GPU[0] : 1: 16.0GT/s x8 GPU[0] : ------------------------------------------------------------------------------------------ ========================================================================================== =================================== % time GPU is busy =================================== GPU[0] : GPU use (%): 7 ========================================================================================== =================================== Current Memory Use =================================== GPU[0] : GPU Memory Allocated (VRAM%): 7 GPU[0] : GPU Memory Read/Write Activity (%): 1 GPU[0] : Memory Activity: N/A GPU[0] : Avg. Memory Bandwidth: 0 ========================================================================================== ===================================== Memory Vendor ====================================== GPU[0] : GPU memory vendor: micron ========================================================================================== ================================== PCIe Replay Counter =================================== GPU[0] : PCIe Replay Count: 0 ========================================================================================== ===================================== Serial Number ====================================== GPU[0] : get_serial_number, Not supported on the given system GPU[0] : Serial Number: N/A ========================================================================================== ===================================== KFD Processes ====================================== No KFD PIDs currently running ========================================================================================== ================================== GPUs Indexed by PID =================================== No KFD PIDs currently running ========================================================================================== ======================= GPU Memory clock frequencies and voltages ======================== GPU[0] : OD_SCLK: GPU[0] : 0: 500Mhz GPU[0] : 1: 2449Mhz GPU[0] : OD_MCLK: GPU[0] : 0: 97Mhz GPU[0] : 1: 1000Mhz ========================================================================================== ==================================== Current voltage ===================================== GPU[0] : Voltage (mV): 856 ========================================================================================== ======================================= PCI Bus ID ======================================= GPU[0] : PCI Bus: 0000:04:00.0 ========================================================================================== ================================== Firmware Information ================================== GPU[0] : ASD firmware version: 0x210000ef GPU[0] : CE firmware version: 37 GPU[0] : ME firmware version: 64 GPU[0] : MEC firmware version: 131 GPU[0] : MEC2 firmware version: 131 GPU[0] : PFP firmware version: 109 GPU[0] : RLC firmware version: 96 GPU[0] : SDMA firmware version: 85 GPU[0] : SDMA2 firmware version: 85 GPU[0] : SMC firmware version: 00.58.90.00 GPU[0] : SOS firmware version: 0x00210f64 GPU[0] : TA RAS firmware version: 27.00.01.62 GPU[0] : TA XGMI firmware version: 32.00.00.20 GPU[0] : VCN firmware version: 0x04121008 ========================================================================================== ====================================== Product Info ====================================== GPU[0] : Card Series: AMD Radeon RX 6800 XT GPU[0] : Card Model: 0x73bf GPU[0] : Card Vendor: Advanced Micro Devices, Inc. [AMD/ATI] GPU[0] : Card SKU: D412 GPU[0] : Subsystem ID: 0x2328 GPU[0] : Device Rev: 0xc1 GPU[0] : Node ID: 1 GPU[0] : GUID: 27684 GPU[0] : GFX Version: gfx1030 ========================================================================================== ======================================= Pages Info ======================================= GPU[0] : ras, Not supported on the given system ================================= Show Valid sclk Range ================================== GPU[0] : Valid sclk range: 500Mhz - 2449Mhz ========================================================================================== ================================= Show Valid mclk Range ================================== GPU[0] : Valid mclk range: 97Mhz - 1000Mhz ========================================================================================== ================================ Show Valid voltage Range ================================ WARNING: GPU[0] : Voltage curve regions unsupported. ========================================================================================== ================================== Voltage Curve Points ================================== WARNING: GPU[0] : Voltage curve Points unsupported. ========================================================================================== ==================================== Consumed Energy ===================================== GPU[0] : Energy counter: 3095321488 GPU[0] : Accumulated Energy (uJ): 47358419356.79 ========================================================================================== =============================== Current Compute Partition ================================ GPU[0] : Not supported on the given system ========================================================================================== ================================ Current Memory Partition ================================ GPU[0] : Not supported on the given system ========================================================================================== ====================================== GPU Metrics ======================================= GPU[0] : Metric Version and Size (Bytes): 1.3 120 GPU[0] : temperature_edge (C): 55 GPU[0] : temperature_hotspot (C): 58 GPU[0] : temperature_mem (C): 62 GPU[0] : temperature_vrgfx (C): 57 GPU[0] : temperature_vrsoc (C): 58 GPU[0] : temperature_vrmem (C): 60 GPU[0] : average_gfx_activity (%): 5 GPU[0] : average_umc_activity (%): 1 GPU[0] : average_mm_activity (%): 0 GPU[0] : average_socket_power (W): 49 GPU[0] : energy_accumulator (15.259uJ (2^-16)): 3095321537 GPU[0] : system_clock_counter (ns): 82187791116982 GPU[0] : average_gfxclk_frequency (MHz): 36 GPU[0] : average_socclk_frequency (MHz): N/A GPU[0] : average_uclk_frequency (MHz): 990 GPU[0] : average_vclk0_frequency (MHz): 33 GPU[0] : average_dclk0_frequency (MHz): 33 GPU[0] : average_vclk1_frequency (MHz): 33 GPU[0] : average_dclk1_frequency (MHz): 33 GPU[0] : current_gfxclk (MHz): 500 GPU[0] : current_socclk (MHz): 800 GPU[0] : current_uclk (MHz): 1000 GPU[0] : current_vclk0 (MHz): 0 GPU[0] : current_dclk0 (MHz): 0 GPU[0] : current_vclk1 (MHz): 0 GPU[0] : current_dclk1 (MHz): 0 GPU[0] : throttle_status: 0 GPU[0] : current_fan_speed (rpm): 934 GPU[0] : pcie_link_width (Lanes): 8 GPU[0] : pcie_link_speed (0.1 GT/s): 160 GPU[0] : gfx_activity_acc (%): N/A GPU[0] : mem_activity_acc (%): N/A GPU[0] : temperature_hbm (C): ['N/A', 'N/A', 'N/A', 'N/A'] GPU[0] : firmware_timestamp (10ns resolution): 18446744073709551606 GPU[0] : voltage_soc (mV): 943 GPU[0] : voltage_gfx (mV): 881 GPU[0] : voltage_mem (mV): 1356 GPU[0] : indep_throttle_status: 0 GPU[0] : current_socket_power (W): N/A GPU[0] : vcn_activity (%): [0, 'N/A', 'N/A', 'N/A'] GPU[0] : gfxclk_lock_status: N/A GPU[0] : xgmi_link_width: N/A GPU[0] : xgmi_link_speed (Gbps): N/A GPU[0] : pcie_bandwidth_acc (GB/s): N/A GPU[0] : pcie_bandwidth_inst (GB/s): N/A GPU[0] : pcie_l0_to_recov_count_acc (Count): N/A GPU[0] : pcie_replay_count_acc (Count): N/A GPU[0] : pcie_replay_rover_count_acc (Count): N/A GPU[0] : xgmi_read_data_acc (kB): ['N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A'] GPU[0] : xgmi_write_data_acc (kB): ['N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A'] GPU[0] : current_gfxclks (MHz): [500, 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A'] GPU[0] : current_socclks (MHz): [800, 'N/A', 'N/A', 'N/A'] GPU[0] : current_vclk0s (MHz): [0, 'N/A', 'N/A', 'N/A'] GPU[0] : current_dclk0s (MHz): [0, 'N/A', 'N/A', 'N/A'] GPU[0] : jpeg_activity (%): ['N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A'] GPU[0] : pcie_nak_sent_count_acc (Count): N/A GPU[0] : pcie_nak_rcvd_count_acc (Count): N/A GPU[0] : accumulation_counter (Count): N/A GPU[0] : prochot_residency_acc (Count): N/A GPU[0] : ppt_residency_acc (Count): N/A GPU[0] : socket_thm_residency_acc (Count): N/A GPU[0] : vr_thm_residency_acc (Count): N/A GPU[0] : hbm_thm_residency_acc (Count): N/A GPU[0] : pcie_lc_perf_other_end_recovery (Count): N/A GPU[0] : vram_max_bandwidth (GB/s): N/A GPU[0] : xgmi_link_status (Up/Down): ['N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A'] GPU[0] : num_partition: N/A GPU[0] XCP[0] : xcp_stats.gfx_busy_inst (%): ['N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A'] GPU[0] XCP[1] : xcp_stats.gfx_busy_inst (%): ['N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A'] GPU[0] XCP[2] : xcp_stats.gfx_busy_inst (%): ['N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A'] GPU[0] XCP[3] : xcp_stats.gfx_busy_inst (%): ['N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A'] GPU[0] XCP[4] : xcp_stats.gfx_busy_inst (%): ['N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A'] GPU[0] XCP[5] : xcp_stats.gfx_busy_inst (%): ['N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A'] GPU[0] XCP[6] : xcp_stats.gfx_busy_inst (%): ['N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A'] GPU[0] XCP[7] : xcp_stats.gfx_busy_inst (%): ['N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A'] GPU[0] XCP[0] : xcp_stats.jpeg_busy (%): ['N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A'] GPU[0] XCP[1] : xcp_stats.jpeg_busy (%): ['N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A'] GPU[0] XCP[2] : xcp_stats.jpeg_busy (%): ['N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A'] GPU[0] XCP[3] : xcp_stats.jpeg_busy (%): ['N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A'] GPU[0] XCP[4] : xcp_stats.jpeg_busy (%): ['N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A'] GPU[0] XCP[5] : xcp_stats.jpeg_busy (%): ['N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A'] GPU[0] XCP[6] : xcp_stats.jpeg_busy (%): ['N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A'] GPU[0] XCP[7] : xcp_stats.jpeg_busy (%): ['N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A'] GPU[0] XCP[0] : xcp_stats.vcn_busy (%): [0, 'N/A', 'N/A', 'N/A'] GPU[0] XCP[1] : xcp_stats.vcn_busy (%): ['N/A', 'N/A', 'N/A', 'N/A'] GPU[0] XCP[2] : xcp_stats.vcn_busy (%): ['N/A', 'N/A', 'N/A', 'N/A'] GPU[0] XCP[3] : xcp_stats.vcn_busy (%): ['N/A', 'N/A', 'N/A', 'N/A'] GPU[0] XCP[4] : xcp_stats.vcn_busy (%): ['N/A', 'N/A', 'N/A', 'N/A'] GPU[0] XCP[5] : xcp_stats.vcn_busy (%): ['N/A', 'N/A', 'N/A', 'N/A'] GPU[0] XCP[6] : xcp_stats.vcn_busy (%): ['N/A', 'N/A', 'N/A', 'N/A'] GPU[0] XCP[7] : xcp_stats.vcn_busy (%): ['N/A', 'N/A', 'N/A', 'N/A'] GPU[0] XCP[0] : xcp_stats.gfx_busy_acc (Count): ['N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A'] GPU[0] XCP[1] : xcp_stats.gfx_busy_acc (Count): ['N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A'] GPU[0] XCP[2] : xcp_stats.gfx_busy_acc (Count): ['N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A'] GPU[0] XCP[3] : xcp_stats.gfx_busy_acc (Count): ['N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A'] GPU[0] XCP[4] : xcp_stats.gfx_busy_acc (Count): ['N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A'] GPU[0] XCP[5] : xcp_stats.gfx_busy_acc (Count): ['N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A'] GPU[0] XCP[6] : xcp_stats.gfx_busy_acc (Count): ['N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A'] GPU[0] XCP[7] : xcp_stats.gfx_busy_acc (Count): ['N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A'] GPU[0] XCP[0] : xcp_stats.gfx_below_host_limit_acc (%): ['N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A'] GPU[0] XCP[1] : xcp_stats.gfx_below_host_limit_acc (%): ['N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A'] GPU[0] XCP[2] : xcp_stats.gfx_below_host_limit_acc (%): ['N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A'] GPU[0] XCP[3] : xcp_stats.gfx_below_host_limit_acc (%): ['N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A'] GPU[0] XCP[4] : xcp_stats.gfx_below_host_limit_acc (%): ['N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A'] GPU[0] XCP[5] : xcp_stats.gfx_below_host_limit_acc (%): ['N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A'] GPU[0] XCP[6] : xcp_stats.gfx_below_host_limit_acc (%): ['N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A'] GPU[0] XCP[7] : xcp_stats.gfx_below_host_limit_acc (%): ['N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A', 'N/A'] ========================================================================================== ================================== End of ROCm SMI Log =================================== ```
GiteaMirror commented 2026-04-22 15:45:37 -05:00
Author
Owner
Copy Link

@FromCreator commented on GitHub (Jul 10, 2025):

I looked at this again and noticed that OD_SCLK maximum value was way too high. I'm not sure why it is set by default to such a high value for a 6800XT. By testing and some guesswork I found that setting it to 1800MHz using CoreCtrl completely solves the issue. Looking at my GPU specs on techpowerup:

Base Clock
1825 MHz
Game Clock
2015 MHz
Boost Clock
2250 MHz

I'm guessing that the base clock value is the stable value. I'm not sure why the higher clocks would be unstable, I have a more than adequate power supply. I am closing this issue, but it is open to anyone who knows a bit more about this than I do.

<!-- gh-comment-id:3058440705 --> @FromCreator commented on GitHub (Jul 10, 2025): I looked at this again and noticed that `OD_SCLK` maximum value was way too high. I'm not sure why it is set by default to such a high value for a 6800XT. By testing and some guesswork I found that setting it to 1800MHz using CoreCtrl completely solves the issue. Looking at my GPU specs on techpowerup: ``` Base Clock 1825 MHz Game Clock 2015 MHz Boost Clock 2250 MHz ``` I'm guessing that the base clock value is the stable value. I'm not sure why the higher clocks would be unstable, I have a more than adequate power supply. I am closing this issue, but it is open to anyone who knows a bit more about this than I do.
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#33247
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?