github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-05 23:53:43 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #3497] Support AMD Firepro w7100 - gfx802 / gfx805 #2153

New Issue
Closed
opened 2026-04-12 12:22:55 -05:00 by GiteaMirror · 1 comment
GiteaMirror commented 2026-04-12 12:22:55 -05:00
Owner
Copy Link

Originally created by @ninp0 on GitHub (Apr 4, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/3497

What are you trying to do?

Start ollama in a manner that will leverage an AMD Firepro w7100 gpu

How should we solve this?

Current output when starting ollama via:

$ sudo systemctl status ollama

● ollama.service - Ollama Service
     Loaded: loaded (/etc/systemd/system/ollama.service; enabled; preset: disabled)
     Active: active (running) since Thu 2024-04-04 16:16:50 MDT; 6min ago
   Main PID: 4404 (ollama)
      Tasks: 21 (limit: 619005)
     Memory: 471.9M (peak: 474.8M)
        CPU: 9.896s
     CGroup: /system.slice/ollama.service
             └─4404 /usr/local/bin/ollama serve

Apr 04 16:16:55 ollama[4404]: time=2024-04-04T16:16:55.990-06:00 level=INFO source=gpu.go:265 msg="Searching for GPU management library libcudart.so*"
Apr 04 16:16:55  ollama[4404]: time=2024-04-04T16:16:55.996-06:00 level=INFO source=gpu.go:311 msg="Discovered GPU libraries: [/tmp/ollama2232459459/runners/cuda_v11/libcudart.so.11.0]"
Apr 04 16:16:55 ollama[4404]: time=2024-04-04T16:16:55.996-06:00 level=INFO source=gpu.go:340 msg="Unable to load cudart CUDA management library /tmp/ollama2232459459/runners/cuda_v11/libcudart.so.11.0: cudart init failure: 35"
...
Apr 04 16:16:56 ollama[4404]: time=2024-04-04T16:16:56.002-06:00 level=WARN source=amd_linux.go:53 msg="ollama recommends running the https://www.amd.com/en/support/linux-drivers: amdgpu version file missing: /sys/module/amdgpu/version stat /sys/module/amdgpu/version: no such file or directory"
Apr 04 16:16:56 ollama[4404]: time=2024-04-04T16:16:56.002-06:00 level=INFO source=amd_linux.go:88 msg="detected amdgpu versions [gfx000 gfx000 gfx000]"
Apr 04 16:16:56 ollama[4404]: time=2024-04-04T16:16:56.002-06:00 level=INFO source=amd_linux.go:92 msg="all detected amdgpus are skipped, falling back to CPU"
Apr 04 16:16:56 ollama[4404]: time=2024-04-04T16:16:56.002-06:00 level=INFO source=routes.go:1141 msg="no GPU detected"

amdgpu modules are loaded:

$ lsmod | grep amdgpu
amdgpu              11554816  0
amdxcp                 12288  1 amdgpu
drm_exec               16384  1 amdgpu
drm_buddy              20480  1 amdgpu
gpu_sched              57344  1 amdgpu
video                  77824  1 amdgpu
drm_suballoc_helper    12288  1 amdgpu
drm_display_helper    233472  1 amdgpu
drm_ttm_helper         12288  1 amdgpu
i2c_algo_bit           12288  2 mgag200,amdgpu
ttm                   106496  2 amdgpu,drm_ttm_helper
drm_kms_helper        270336  5 drm_display_helper,mgag200,amdgpu
drm                   802816  14 gpu_sched,drm_kms_helper,drm_exec,drm_suballoc_helper,drm_shmem_helper,drm_display_helper,mgag200,drm_buddy,amdgpu,drm_ttm_helper,ttm,amdxcp

$ sudo lspci -s 44:00.0 -vv
44:00.0 VGA compatible controller: Advanced Micro Devices, Inc. [AMD/ATI] Tonga PRO GL [FirePro W7100 / Barco MXRT-7600] (prog-if 00 [VGA controller])
        Subsystem: BARCO Tonga PRO GL [FirePro W7100 / Barco MXRT-7600]
        Control: I/O+ Mem+ BusMaster- SpecCycle- MemWINV- VGASnoop- ParErr- Stepping- SERR- FastB2B- DisINTx-
        Status: Cap+ 66MHz- UDF- FastB2B- ParErr- DEVSEL=fast >TAbort- <TAbort- <MAbort- >SERR- <PERR- INTx-
        Interrupt: pin A routed to IRQ 80
        NUMA node: 1
        IOMMU group: 8
        Region 0: Memory at 3bff0000000 (64-bit, prefetchable) [size=256M]
        Region 2: Memory at 3bfefe00000 (64-bit, prefetchable) [size=2M]
        Region 4: I/O ports at dc00 [size=256]
        Region 5: Memory at d4fc0000 (32-bit, non-prefetchable) [size=256K]
        Expansion ROM at d4000000 [disabled] [size=128K]
        Capabilities: [48] Vendor Specific Information: Len=08 <?>
        Capabilities: [50] Power Management version 3
                Flags: PMEClk- DSI- D1+ D2+ AuxCurrent=0mA PME(D0-,D1+,D2+,D3hot+,D3cold+)
                Status: D0 NoSoftRst+ PME-Enable- DSel=0 DScale=0 PME-
        Capabilities: [58] Express (v2) Legacy Endpoint, MSI 00
                DevCap: MaxPayload 256 bytes, PhantFunc 0, Latency L0s <4us, L1 unlimited
                        ExtTag+ AttnBtn- AttnInd- PwrInd- RBE+ FLReset-
                DevCtl: CorrErr+ NonFatalErr+ FatalErr+ UnsupReq+
                        RlxdOrd+ ExtTag+ PhantFunc- AuxPwr- NoSnoop+
                        MaxPayload 256 bytes, MaxReadReq 512 bytes
                DevSta: CorrErr+ NonFatalErr- FatalErr- UnsupReq+ AuxPwr- TransPend-
                LnkCap: Port #0, Speed 8GT/s, Width x16, ASPM L0s L1, Exit Latency L0s <64ns, L1 <1us
                        ClockPM- Surprise- LLActRep- BwNot- ASPMOptComp+
                LnkCtl: ASPM Disabled; RCB 64 bytes, Disabled- CommClk+
                        ExtSynch- ClockPM- AutWidDis- BWInt- AutBWInt-
                LnkSta: Speed 8GT/s, Width x16
                        TrErr- Train- SlotClk+ DLActive- BWMgmt- ABWMgmt-
                DevCap2: Completion Timeout: Not Supported, TimeoutDis- NROPrPrP- LTR-
                         10BitTagComp- 10BitTagReq- OBFF Not Supported, ExtFmt+ EETLPPrefix+, MaxEETLPPrefixes 1
                         EmergencyPowerReduction Not Supported, EmergencyPowerReductionInit-
                         FRS-
                         AtomicOpsCap: 32bit- 64bit- 128bitCAS-
                DevCtl2: Completion Timeout: 50us to 50ms, TimeoutDis- LTR- 10BitTagReq- OBFF Disabled,
                         AtomicOpsCtl: ReqEn-
                LnkCap2: Supported Link Speeds: 2.5-8GT/s, Crosslink- Retimer- 2Retimers- DRS-
                LnkCtl2: Target Link Speed: 8GT/s, EnterCompliance- SpeedDis-
                         Transmit Margin: Normal Operating Range, EnterModifiedCompliance- ComplianceSOS-
                         Compliance Preset/De-emphasis: -6dB de-emphasis, 0dB preshoot
                LnkSta2: Current De-emphasis Level: -6dB, EqualizationComplete+ EqualizationPhase1+
                         EqualizationPhase2+ EqualizationPhase3+ LinkEqualizationRequest-
                         Retimer- 2Retimers- CrosslinkRes: unsupported
        Capabilities: [a0] MSI: Enable- Count=1/1 Maskable- 64bit+
                Address: 0000000000000000  Data: 0000
        Capabilities: [100 v1] Vendor Specific Information: ID=0001 Rev=1 Len=010 <?>
        Capabilities: [150 v2] Advanced Error Reporting
                UESta:  DLP- SDES- TLP- FCP- CmpltTO- CmpltAbrt- UnxCmplt- RxOF- MalfTLP- ECRC- UnsupReq- ACSViol-
                UEMsk:  DLP- SDES- TLP- FCP- CmpltTO- CmpltAbrt- UnxCmplt+ RxOF- MalfTLP- ECRC- UnsupReq- ACSViol-
                UESvrt: DLP+ SDES+ TLP+ FCP+ CmpltTO+ CmpltAbrt- UnxCmplt- RxOF+ MalfTLP+ ECRC+ UnsupReq- ACSViol-
                CESta:  RxErr- BadTLP- BadDLLP- Rollover- Timeout- AdvNonFatalErr-
                CEMsk:  RxErr- BadTLP+ BadDLLP+ Rollover+ Timeout+ AdvNonFatalErr+
                AERCap: First Error Pointer: 00, ECRCGenCap+ ECRCGenEn- ECRCChkCap+ ECRCChkEn-
                        MultHdrRecCap- MultHdrRecEn- TLPPfxPres- HdrLogCap-
                HeaderLog: 00000000 00000000 00000000 00000000
        Capabilities: [200 v1] Physical Resizable BAR
                BAR 0: current size: 256MB, supported: 256MB 512MB 1GB 2GB 4GB 8GB
        Capabilities: [270 v1] Secondary PCI Express
                LnkCtl3: LnkEquIntrruptEn- PerformEqu-
                LaneErrStat: 0
        Capabilities: [2b0 v1] Address Translation Service (ATS)
                ATSCap: Invalidate Queue Depth: 00
                ATSCtl: Enable+, Smallest Translation Unit: 00
        Capabilities: [2c0 v1] Page Request Interface (PRI)
                PRICtl: Enable- Reset-
                PRISta: RF- UPRGI- Stopped+
                Page Request Capacity: 00000020, Page Request Allocation: 00000000
        Capabilities: [2d0 v1] Process Address Space ID (PASID)
                PASIDCap: Exec+ Priv+, Max PASID Width: 10
                PASIDCtl: Enable- Exec- Priv-
        Capabilities: [328 v1] Alternative Routing-ID Interpretation (ARI)
                ARICap: MFVC- ACS-, Next Function: 0
                ARICtl: MFVC- ACS-, Function Group: 0
        Kernel modules: amdgpu

What is the impact of not solving this?

ollama won't use GPU.

Anything else?

I'm hoping this can be addressed by simply mapping to an appropriate version? The error in the sudo systemctl status ollama is leading me to that conclusion: /sys/module/amdgpu/version: no such file or directory

That said, I did try this which appeared to fail as well:

# systemctl stop ollama && HSA_OVERRIDE_GFX_VERSION=10.3.0 ollama serve

time=2024-04-04T16:48:07.577-06:00 level=INFO source=images.go:804 msg="total blobs: 0"
time=2024-04-04T16:48:07.578-06:00 level=INFO source=images.go:811 msg="total unused blobs removed: 0"
time=2024-04-04T16:48:07.578-06:00 level=INFO source=routes.go:1118 msg="Listening on 127.0.0.1:11434 (version 0.1.30)"
time=2024-04-04T16:48:07.579-06:00 level=INFO source=payload_common.go:113 msg="Extracting dynamic libraries to /tmp/ollama718362879/runners ..."
time=2024-04-04T16:48:14.009-06:00 level=INFO source=payload_common.go:140 msg="Dynamic LLM libraries [cpu_avx cuda_v11 cpu cpu_avx2 rocm_v60000]"
time=2024-04-04T16:48:14.009-06:00 level=INFO source=gpu.go:115 msg="Detecting GPU type"
time=2024-04-04T16:48:14.009-06:00 level=INFO source=gpu.go:265 msg="Searching for GPU management library libcudart.so*"
time=2024-04-04T16:48:14.015-06:00 level=INFO source=gpu.go:311 msg="Discovered GPU libraries: [/tmp/ollama718362879/runners/cuda_v11/libcudart.so.11.0]"
time=2024-04-04T16:48:14.016-06:00 level=INFO source=gpu.go:340 msg="Unable to load cudart CUDA management library /tmp/ollama718362879/runners/cuda_v11/libcudart.so.11.0: cudart init failure: 35"
time=2024-04-04T16:48:14.016-06:00 level=INFO source=gpu.go:265 msg="Searching for GPU management library libnvidia-ml.so"
time=2024-04-04T16:48:14.022-06:00 level=INFO source=gpu.go:311 msg="Discovered GPU libraries: []"
time=2024-04-04T16:48:14.022-06:00 level=INFO source=cpu_common.go:15 msg="CPU has AVX"
time=2024-04-04T16:48:14.023-06:00 level=WARN source=amd_linux.go:53 msg="ollama recommends running the https://www.amd.com/en/support/linux-drivers: amdgpu version file missing: /sys/module/amdgpu/version stat /sys/module/amdgpu/version: no such file or directory"
time=2024-04-04T16:48:14.023-06:00 level=INFO source=amd_linux.go:88 msg="detected amdgpu versions [gfx000 gfx000 gfx000]"
time=2024-04-04T16:48:14.023-06:00 level=INFO source=amd_linux.go:92 msg="all detected amdgpus are skipped, falling back to CPU"
time=2024-04-04T16:48:14.023-06:00 level=INFO source=routes.go:1141 msg="no GPU detected"
Originally created by @ninp0 on GitHub (Apr 4, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/3497 ### What are you trying to do? Start ollama in a manner that will leverage an AMD Firepro w7100 gpu ### How should we solve this? Current output when starting ollama via: ``` $ sudo systemctl status ollama ● ollama.service - Ollama Service Loaded: loaded (/etc/systemd/system/ollama.service; enabled; preset: disabled) Active: active (running) since Thu 2024-04-04 16:16:50 MDT; 6min ago Main PID: 4404 (ollama) Tasks: 21 (limit: 619005) Memory: 471.9M (peak: 474.8M) CPU: 9.896s CGroup: /system.slice/ollama.service └─4404 /usr/local/bin/ollama serve Apr 04 16:16:55 ollama[4404]: time=2024-04-04T16:16:55.990-06:00 level=INFO source=gpu.go:265 msg="Searching for GPU management library libcudart.so*" Apr 04 16:16:55 ollama[4404]: time=2024-04-04T16:16:55.996-06:00 level=INFO source=gpu.go:311 msg="Discovered GPU libraries: [/tmp/ollama2232459459/runners/cuda_v11/libcudart.so.11.0]" Apr 04 16:16:55 ollama[4404]: time=2024-04-04T16:16:55.996-06:00 level=INFO source=gpu.go:340 msg="Unable to load cudart CUDA management library /tmp/ollama2232459459/runners/cuda_v11/libcudart.so.11.0: cudart init failure: 35" ... Apr 04 16:16:56 ollama[4404]: time=2024-04-04T16:16:56.002-06:00 level=WARN source=amd_linux.go:53 msg="ollama recommends running the https://www.amd.com/en/support/linux-drivers: amdgpu version file missing: /sys/module/amdgpu/version stat /sys/module/amdgpu/version: no such file or directory" Apr 04 16:16:56 ollama[4404]: time=2024-04-04T16:16:56.002-06:00 level=INFO source=amd_linux.go:88 msg="detected amdgpu versions [gfx000 gfx000 gfx000]" Apr 04 16:16:56 ollama[4404]: time=2024-04-04T16:16:56.002-06:00 level=INFO source=amd_linux.go:92 msg="all detected amdgpus are skipped, falling back to CPU" Apr 04 16:16:56 ollama[4404]: time=2024-04-04T16:16:56.002-06:00 level=INFO source=routes.go:1141 msg="no GPU detected" ``` amdgpu modules are loaded: ``` $ lsmod | grep amdgpu amdgpu 11554816 0 amdxcp 12288 1 amdgpu drm_exec 16384 1 amdgpu drm_buddy 20480 1 amdgpu gpu_sched 57344 1 amdgpu video 77824 1 amdgpu drm_suballoc_helper 12288 1 amdgpu drm_display_helper 233472 1 amdgpu drm_ttm_helper 12288 1 amdgpu i2c_algo_bit 12288 2 mgag200,amdgpu ttm 106496 2 amdgpu,drm_ttm_helper drm_kms_helper 270336 5 drm_display_helper,mgag200,amdgpu drm 802816 14 gpu_sched,drm_kms_helper,drm_exec,drm_suballoc_helper,drm_shmem_helper,drm_display_helper,mgag200,drm_buddy,amdgpu,drm_ttm_helper,ttm,amdxcp ``` ``` $ sudo lspci -s 44:00.0 -vv 44:00.0 VGA compatible controller: Advanced Micro Devices, Inc. [AMD/ATI] Tonga PRO GL [FirePro W7100 / Barco MXRT-7600] (prog-if 00 [VGA controller]) Subsystem: BARCO Tonga PRO GL [FirePro W7100 / Barco MXRT-7600] Control: I/O+ Mem+ BusMaster- SpecCycle- MemWINV- VGASnoop- ParErr- Stepping- SERR- FastB2B- DisINTx- Status: Cap+ 66MHz- UDF- FastB2B- ParErr- DEVSEL=fast >TAbort- <TAbort- <MAbort- >SERR- <PERR- INTx- Interrupt: pin A routed to IRQ 80 NUMA node: 1 IOMMU group: 8 Region 0: Memory at 3bff0000000 (64-bit, prefetchable) [size=256M] Region 2: Memory at 3bfefe00000 (64-bit, prefetchable) [size=2M] Region 4: I/O ports at dc00 [size=256] Region 5: Memory at d4fc0000 (32-bit, non-prefetchable) [size=256K] Expansion ROM at d4000000 [disabled] [size=128K] Capabilities: [48] Vendor Specific Information: Len=08 <?> Capabilities: [50] Power Management version 3 Flags: PMEClk- DSI- D1+ D2+ AuxCurrent=0mA PME(D0-,D1+,D2+,D3hot+,D3cold+) Status: D0 NoSoftRst+ PME-Enable- DSel=0 DScale=0 PME- Capabilities: [58] Express (v2) Legacy Endpoint, MSI 00 DevCap: MaxPayload 256 bytes, PhantFunc 0, Latency L0s <4us, L1 unlimited ExtTag+ AttnBtn- AttnInd- PwrInd- RBE+ FLReset- DevCtl: CorrErr+ NonFatalErr+ FatalErr+ UnsupReq+ RlxdOrd+ ExtTag+ PhantFunc- AuxPwr- NoSnoop+ MaxPayload 256 bytes, MaxReadReq 512 bytes DevSta: CorrErr+ NonFatalErr- FatalErr- UnsupReq+ AuxPwr- TransPend- LnkCap: Port #0, Speed 8GT/s, Width x16, ASPM L0s L1, Exit Latency L0s <64ns, L1 <1us ClockPM- Surprise- LLActRep- BwNot- ASPMOptComp+ LnkCtl: ASPM Disabled; RCB 64 bytes, Disabled- CommClk+ ExtSynch- ClockPM- AutWidDis- BWInt- AutBWInt- LnkSta: Speed 8GT/s, Width x16 TrErr- Train- SlotClk+ DLActive- BWMgmt- ABWMgmt- DevCap2: Completion Timeout: Not Supported, TimeoutDis- NROPrPrP- LTR- 10BitTagComp- 10BitTagReq- OBFF Not Supported, ExtFmt+ EETLPPrefix+, MaxEETLPPrefixes 1 EmergencyPowerReduction Not Supported, EmergencyPowerReductionInit- FRS- AtomicOpsCap: 32bit- 64bit- 128bitCAS- DevCtl2: Completion Timeout: 50us to 50ms, TimeoutDis- LTR- 10BitTagReq- OBFF Disabled, AtomicOpsCtl: ReqEn- LnkCap2: Supported Link Speeds: 2.5-8GT/s, Crosslink- Retimer- 2Retimers- DRS- LnkCtl2: Target Link Speed: 8GT/s, EnterCompliance- SpeedDis- Transmit Margin: Normal Operating Range, EnterModifiedCompliance- ComplianceSOS- Compliance Preset/De-emphasis: -6dB de-emphasis, 0dB preshoot LnkSta2: Current De-emphasis Level: -6dB, EqualizationComplete+ EqualizationPhase1+ EqualizationPhase2+ EqualizationPhase3+ LinkEqualizationRequest- Retimer- 2Retimers- CrosslinkRes: unsupported Capabilities: [a0] MSI: Enable- Count=1/1 Maskable- 64bit+ Address: 0000000000000000 Data: 0000 Capabilities: [100 v1] Vendor Specific Information: ID=0001 Rev=1 Len=010 <?> Capabilities: [150 v2] Advanced Error Reporting UESta: DLP- SDES- TLP- FCP- CmpltTO- CmpltAbrt- UnxCmplt- RxOF- MalfTLP- ECRC- UnsupReq- ACSViol- UEMsk: DLP- SDES- TLP- FCP- CmpltTO- CmpltAbrt- UnxCmplt+ RxOF- MalfTLP- ECRC- UnsupReq- ACSViol- UESvrt: DLP+ SDES+ TLP+ FCP+ CmpltTO+ CmpltAbrt- UnxCmplt- RxOF+ MalfTLP+ ECRC+ UnsupReq- ACSViol- CESta: RxErr- BadTLP- BadDLLP- Rollover- Timeout- AdvNonFatalErr- CEMsk: RxErr- BadTLP+ BadDLLP+ Rollover+ Timeout+ AdvNonFatalErr+ AERCap: First Error Pointer: 00, ECRCGenCap+ ECRCGenEn- ECRCChkCap+ ECRCChkEn- MultHdrRecCap- MultHdrRecEn- TLPPfxPres- HdrLogCap- HeaderLog: 00000000 00000000 00000000 00000000 Capabilities: [200 v1] Physical Resizable BAR BAR 0: current size: 256MB, supported: 256MB 512MB 1GB 2GB 4GB 8GB Capabilities: [270 v1] Secondary PCI Express LnkCtl3: LnkEquIntrruptEn- PerformEqu- LaneErrStat: 0 Capabilities: [2b0 v1] Address Translation Service (ATS) ATSCap: Invalidate Queue Depth: 00 ATSCtl: Enable+, Smallest Translation Unit: 00 Capabilities: [2c0 v1] Page Request Interface (PRI) PRICtl: Enable- Reset- PRISta: RF- UPRGI- Stopped+ Page Request Capacity: 00000020, Page Request Allocation: 00000000 Capabilities: [2d0 v1] Process Address Space ID (PASID) PASIDCap: Exec+ Priv+, Max PASID Width: 10 PASIDCtl: Enable- Exec- Priv- Capabilities: [328 v1] Alternative Routing-ID Interpretation (ARI) ARICap: MFVC- ACS-, Next Function: 0 ARICtl: MFVC- ACS-, Function Group: 0 Kernel modules: amdgpu ``` ### What is the impact of not solving this? ollama won't use GPU. ### Anything else? I'm hoping this can be addressed by simply mapping to an appropriate version? The error in the `sudo systemctl status ollama` is leading me to that conclusion: `/sys/module/amdgpu/version: no such file or directory` That said, I did try this which appeared to fail as well: ``` # systemctl stop ollama && HSA_OVERRIDE_GFX_VERSION=10.3.0 ollama serve time=2024-04-04T16:48:07.577-06:00 level=INFO source=images.go:804 msg="total blobs: 0" time=2024-04-04T16:48:07.578-06:00 level=INFO source=images.go:811 msg="total unused blobs removed: 0" time=2024-04-04T16:48:07.578-06:00 level=INFO source=routes.go:1118 msg="Listening on 127.0.0.1:11434 (version 0.1.30)" time=2024-04-04T16:48:07.579-06:00 level=INFO source=payload_common.go:113 msg="Extracting dynamic libraries to /tmp/ollama718362879/runners ..." time=2024-04-04T16:48:14.009-06:00 level=INFO source=payload_common.go:140 msg="Dynamic LLM libraries [cpu_avx cuda_v11 cpu cpu_avx2 rocm_v60000]" time=2024-04-04T16:48:14.009-06:00 level=INFO source=gpu.go:115 msg="Detecting GPU type" time=2024-04-04T16:48:14.009-06:00 level=INFO source=gpu.go:265 msg="Searching for GPU management library libcudart.so*" time=2024-04-04T16:48:14.015-06:00 level=INFO source=gpu.go:311 msg="Discovered GPU libraries: [/tmp/ollama718362879/runners/cuda_v11/libcudart.so.11.0]" time=2024-04-04T16:48:14.016-06:00 level=INFO source=gpu.go:340 msg="Unable to load cudart CUDA management library /tmp/ollama718362879/runners/cuda_v11/libcudart.so.11.0: cudart init failure: 35" time=2024-04-04T16:48:14.016-06:00 level=INFO source=gpu.go:265 msg="Searching for GPU management library libnvidia-ml.so" time=2024-04-04T16:48:14.022-06:00 level=INFO source=gpu.go:311 msg="Discovered GPU libraries: []" time=2024-04-04T16:48:14.022-06:00 level=INFO source=cpu_common.go:15 msg="CPU has AVX" time=2024-04-04T16:48:14.023-06:00 level=WARN source=amd_linux.go:53 msg="ollama recommends running the https://www.amd.com/en/support/linux-drivers: amdgpu version file missing: /sys/module/amdgpu/version stat /sys/module/amdgpu/version: no such file or directory" time=2024-04-04T16:48:14.023-06:00 level=INFO source=amd_linux.go:88 msg="detected amdgpu versions [gfx000 gfx000 gfx000]" time=2024-04-04T16:48:14.023-06:00 level=INFO source=amd_linux.go:92 msg="all detected amdgpus are skipped, falling back to CPU" time=2024-04-04T16:48:14.023-06:00 level=INFO source=routes.go:1141 msg="no GPU detected" ```
GiteaMirror commented 2026-04-12 12:22:56 -05:00
Author
Owner
Copy Link

@dhiltgen commented on GitHub (Apr 12, 2024):

It looks like this is an older card, in the gfx800 family, which has fallen off the support matrix for ROCm. We're tracking support for these older cards in #2453

It's unlikely we'll be able to add support for these in the official binaries, but our hope is to be able to enable people to build from source if they install an older EOL rocm version which had support for these cards.

<!-- gh-comment-id:2052692645 --> @dhiltgen commented on GitHub (Apr 12, 2024): It looks like this is an older card, in the gfx800 family, which has fallen off the support matrix for ROCm. We're tracking support for these older cards in #2453 It's unlikely we'll be able to add support for these in the official binaries, but our hope is to be able to enable people to build from source if they install an older EOL rocm version which had support for these cards.
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
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#2153
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?