LocalAI version:
localai/localai:latest-gpu-hipblas or localai/localai:latest-gpu-vulkan.
LocalAI v4.5.6 (02b007a)
Environment, CPU architecture, OS, and Version:
Linux minisforum 7.0.0-27-generic #27-Ubuntu SMP PREEMPT_DYNAMIC Thu Jun 18 19:13:49 UTC 2026 x86_64 GNU/Linux
alexander@minisforum:/srv$ rocminfo
ROCk module is loaded
=====================
HSA System Attributes
=====================
Runtime Version: 1.1
Runtime Ext Version: 1.14
System Timestamp Freq.: 1000.000000MHz
Sig. Max Wait Duration: 18446744073709551615 (0xFFFFFFFFFFFFFFFF) (timestamp count)
Machine Model: LARGE
System Endianness: LITTLE
Mwaitx: DISABLED
XNACK enabled: NO
DMAbuf Support: YES
VMM Support: YES
==========
HSA Agents
==========
*******
Agent 1
*******
Name: AMD Ryzen AI 9 HX 370 w/ Radeon 890M
Uuid: CPU-XX
Marketing Name: AMD Ryzen AI 9 HX 370 w/ Radeon 890M
Vendor Name: CPU
Feature: None specified
Profile: FULL_PROFILE
Float Round Mode: NEAR
Max Queue Number: 0(0x0)
Queue Min Size: 0(0x0)
Queue Max Size: 0(0x0)
Queue Type: MULTI
Node: 0
Device Type: CPU
Cache Info:
L1: 49152(0xc000) KB
Chip ID: 0(0x0)
ASIC Revision: 0(0x0)
Cacheline Size: 64(0x40)
Max Clock Freq. (MHz): 5157
BDFID: 0
Internal Node ID: 0
Compute Unit: 24
SIMDs per CU: 0
Shader Engines: 0
Shader Arrs. per Eng.: 0
WatchPts on Addr. Ranges:1
Memory Properties:
Features: None
Pool Info:
Pool 1
Segment: GLOBAL; FLAGS: FINE GRAINED
Size: 47876696(0x2da8a58) KB
Allocatable: TRUE
Alloc Granule: 4KB
Alloc Recommended Granule:4KB
Alloc Alignment: 4KB
Accessible by all: TRUE
Pool 2
Segment: GLOBAL; FLAGS: EXTENDED FINE GRAINED
Size: 47876696(0x2da8a58) KB
Allocatable: TRUE
Alloc Granule: 4KB
Alloc Recommended Granule:4KB
Alloc Alignment: 4KB
Accessible by all: TRUE
Pool 3
Segment: GLOBAL; FLAGS: KERNARG, FINE GRAINED
Size: 47876696(0x2da8a58) KB
Allocatable: TRUE
Alloc Granule: 4KB
Alloc Recommended Granule:4KB
Alloc Alignment: 4KB
Accessible by all: TRUE
Pool 4
Segment: GLOBAL; FLAGS: COARSE GRAINED
Size: 47876696(0x2da8a58) KB
Allocatable: TRUE
Alloc Granule: 4KB
Alloc Recommended Granule:4KB
Alloc Alignment: 4KB
Accessible by all: TRUE
ISA Info:
*******
Agent 2
*******
Name: gfx1150
Uuid: GPU-XX
Marketing Name: AMD Radeon 890M Graphics
Vendor Name: AMD
Feature: KERNEL_DISPATCH
Profile: BASE_PROFILE
Float Round Mode: NEAR
Max Queue Number: 128(0x80)
Queue Min Size: 64(0x40)
Queue Max Size: 131072(0x20000)
Queue Type: MULTI
Node: 1
Device Type: GPU
Cache Info:
L1: 32(0x20) KB
L2: 2048(0x800) KB
Chip ID: 5390(0x150e)
ASIC Revision: 4(0x4)
Cacheline Size: 128(0x80)
Max Clock Freq. (MHz): 2900
BDFID: 50688
Internal Node ID: 1
Compute Unit: 16
SIMDs per CU: 2
Shader Engines: 1
Shader Arrs. per Eng.: 2
WatchPts on Addr. Ranges:4
Coherent Host Access: FALSE
Memory Properties: APU
Features: KERNEL_DISPATCH
Fast F16 Operation: TRUE
Wavefront Size: 32(0x20)
Workgroup Max Size: 1024(0x400)
Workgroup Max Size per Dimension:
x 1024(0x400)
y 1024(0x400)
z 1024(0x400)
Max Waves Per CU: 32(0x20)
Max Work-item Per CU: 1024(0x400)
Grid Max Size: 4294967295(0xffffffff)
Grid Max Size per Dimension:
x 2147483647(0x7fffffff)
y 65535(0xffff)
z 65535(0xffff)
Max fbarriers/Workgrp: 32
Packet Processor uCode:: 34
SDMA engine uCode:: 15
IOMMU Support:: None
Pool Info:
Pool 1
Segment: GLOBAL; FLAGS: COARSE GRAINED
Size: 94371840(0x5a00000) KB
Allocatable: TRUE
Alloc Granule: 4KB
Alloc Recommended Granule:2048KB
Alloc Alignment: 4KB
Accessible by all: FALSE
Pool 2
Segment: GLOBAL; FLAGS: EXTENDED FINE GRAINED
Size: 94371840(0x5a00000) KB
Allocatable: TRUE
Alloc Granule: 4KB
Alloc Recommended Granule:2048KB
Alloc Alignment: 4KB
Accessible by all: FALSE
Pool 3
Segment: GROUP
Size: 64(0x40) KB
Allocatable: FALSE
Alloc Granule: 0KB
Alloc Recommended Granule:0KB
Alloc Alignment: 0KB
Accessible by all: FALSE
ISA Info:
ISA 1
Name: amdgcn-amd-amdhsa--gfx1150
Machine Models: HSA_MACHINE_MODEL_LARGE
Profiles: HSA_PROFILE_BASE
Default Rounding Mode: NEAR
Default Rounding Mode: NEAR
Fast f16: TRUE
Workgroup Max Size: 1024(0x400)
Workgroup Max Size per Dimension:
x 1024(0x400)
y 1024(0x400)
z 1024(0x400)
Grid Max Size: 4294967295(0xffffffff)
Grid Max Size per Dimension:
x 2147483647(0x7fffffff)
y 65535(0xffff)
z 65535(0xffff)
FBarrier Max Size: 32
ISA 2
Name: amdgcn-amd-amdhsa--gfx11-generic
Machine Models: HSA_MACHINE_MODEL_LARGE
Profiles: HSA_PROFILE_BASE
Default Rounding Mode: NEAR
Default Rounding Mode: NEAR
Fast f16: TRUE
Workgroup Max Size: 1024(0x400)
Workgroup Max Size per Dimension:
x 1024(0x400)
y 1024(0x400)
z 1024(0x400)
Grid Max Size: 4294967295(0xffffffff)
Grid Max Size per Dimension:
x 2147483647(0x7fffffff)
y 65535(0xffff)
z 65535(0xffff)
FBarrier Max Size: 32
*** Done ***
GRUB_CMDLINE_LINUX_DEFAULT="quiet splash amdgpu.vm_fragment_size=9 amdgpu.vm_update_mode=3 amd_iommu=off ttm.pages_limit=23592960 amdgpu.gttsize=92160"
In UEFI, 48GB out of 96GM RAM is set for frame buffer for AMD iGPU.
docker-compose.yml:
localai:
image: localai/localai:latest-gpu-hipblas
restart: unless-stopped
healthcheck:
test: ["CMD", "curl", "-f", "http://localhost:8080/readyz"]
interval: 1m
timeout: 20m
retries: 5
ports:
- 8080:8080
networks:
- webui
- flowise
extra_hosts:
- "host.docker.internal:host-gateway"
- "nas:192.168.1.104"
environment:
AMD_VISIBLE_DEVICES: all
DEBUG: true
LOCALAI_FORCE_META_BACKEND_CAPABILITY: amd
BUILD_TYPE: hipblas
REBUILD: true
GGML_CUDA_ENABLE_UNIFIED_MEMORY: 1
LOCALAI_AGENT_POOL_DEFAULT_MODEL: hermes-3-llama3.1-8b
LOCALAI_AGENT_POOL_EMBEDDING_MODEL: granite-embedding-107m-multilingual
LOCALAI_AGENT_POOL_ENABLE_SKILLS: true
LOCALAI_AGENT_POOL_ENABLE_LOGS: true
LOCALAI_AGENT_POOL_VECTOR_ENGINE: postgres
LOCALAI_AGENT_POOL_DATABASE_URL: [redacted]
LOCALAI_API_KEY: [redacted]
# user: "${UID}:${GID}"
volumes:
- models:/models:rw
- backends:/backends:rw
- data:/data:rw
- config:/etc/localai:rw
- configuration:/configuration:rw
- content:/tmp/generated/content:rw
group_add:
- video
- render
runtime: amd
devices:
- /dev/kfd:/dev/kfd
- /dev/dri:/dev/driDescribe the bug
An attempt to generate an image with any model, afre less than a minute, shows an error message: "Error: NetworkError when attempting to fetch resource." (by the way, it is too geneic to be of use).
To Reproduce
On Studio page, try to generate an image from a prompt using an installed Stable diffusion or Diffusers model.
Expected behavior
An image is shown after some time.
Logs
The API trace says: "failed to load model with internal loader: could not load model: rpc error: code = Canceled desc = context canceled" (again, a uselessly generic message),
The backend trace is:
03:32:36.873stdoutInitializing libbackend for rocm-diffusers
03:32:36.875stdoutUsing portable Python
03:32:36.939stdoutAdded /backends/rocm-diffusers/lib to LD_LIBRARY_PATH for GPU libraries
03:32:38.504stderr/backends/rocm-diffusers/venv/lib/python3.10/site-packages/transformers/utils/hub.py:110: FutureWarning: Using `TRANSFORMERS_CACHE` is deprecated and will be removed in v5 of Transformers. Use `HF_HOME` instead.
03:32:38.504stderr warnings.warn(
03:32:39.162stderrServer started. Listening on: 127.0.0.1:34021
03:32:40.876stderrLoading model lodestones/Chroma1-HD...
03:32:40.876stderrRequest Model: "lodestones/Chroma1-HD"
03:32:40.876stderrContextSize: 4096
03:32:40.876stderrSeed: 1955829538
03:32:40.876stderrNBatch: 512
03:32:40.876stderrMMap: true
03:32:40.877stderrNGPULayers: 99999999
03:32:40.877stderrThreads: 12
03:32:40.877stderrModelFile: "/models/lodestones/Chroma1-HD"
03:32:40.877stderrPipelineType: "ChromaPipeline"
03:32:40.877stderrCFGScale: 3
03:32:40.877stderrFlashAttention: "auto"
03:32:40.877stderrModelPath: "//models"
03:32:40.877stderrOptions: "torch_dtype:bf16"
03:32:40.877stderrOptions: "cache_reuse:256"
03:32:40.877stderrOptions: "parallel:8"
03:32:40.877stderr
03:32:40.877stderrOptions: {'cache_reuse': 256.0, 'parallel': 8.0}
03:32:40.877stderrLoadModel: PipelineType from request: ChromaPipeline
03:32:40.990stderrModular Diffusers is currently an experimental feature under active development. The API is subject to breaking changes in future releases.
03:33:02.284stdoutReceived termination signal. Shutting down...
The relevant container log entries are:
Jul 01 20:32:12 DEBUG GPU count count=1 caller={caller.file="/build/core/application/startup.go" caller.L=61 }
Jul 01 20:32:12 DEBUG GPU gpu="card #0 @0000:c6:00.0 -> driver: 'amdgpu' class: 'Display controller' vendor: 'Advanced Micro Devices, Inc. [AMD/ATI]' product: 'unknown'" caller={caller.file="/build/core/application/startup.go" caller.L=63 }
…
Jul 01 20:32:35 DEBUG context local model name not found, setting to the first model first model name="chroma1-hd" caller={caller.file="/build/core/http/middleware/request.go" caller.L=115 }
Jul 01 20:32:35 DEBUG GPU vendor detected via ghw vendor="amd" caller={caller.file="/build/pkg/xsysinfo/gpu.go" caller.L=219 }
Jul 01 20:32:35 DEBUG HTTP request method="GET" path="/api/operations" status=200 caller={caller.file="/build/core/http/app.go" caller.L=215 }
Jul 01 20:32:35 DEBUG input.Input input="<nil>" caller={caller.file="/build/core/http/middleware/request.go" caller.L=561 }
Jul 01 20:32:35 DEBUG Parameter Config config=&{/models/chroma1-hd.yaml {{lodestones/Chroma1-HD} false 0 0x984e543a7e0 0x984e543a7e8 0x984e543a7f0 0x984e543a7f8 0x984e543a828 <nil> false 0 false 0 0 0 0 0 0x984e543a820 0x984e543a818 0x984e543a830 {false} <nil> map[] 0 0 0 0 } chroma1-hd 0x984e543a758 0x984e543a768 0x984e3d8735a map[] 0x984e543a7db diffusers { false <nil> } [FLAG_VIDEO FLAG_VISION FLAG_IMAGE] 0x984e6015e88 { 0 0 {<nil> <nil> <nil> <nil>} <nil> <nil> <nil> <nil> { <nil>}} [A golden retriever.] [] [] map[] {false {false false false false false false []} [] [] [] [] [] [] <nil> false false <nil>} {<nil> <nil> <nil> [] []} map[] map[] map[] { 0 0 0x984e543a7da false 0x984e543a810 0x984e543a808 0x984e543a800 <nil> 0x984e543a7da 0x984e543a7db 0x984e543a7db 0x984e543a7db [] [] [] [] [] <nil> false [] [] 0 false 0 0 false false 0 0 0 false {0 0 0} map[] <nil> false 0 0 0 0 3} {false ChromaPipeline false 0 } 40 {0 0} { } false [] <nil> <nil> [] [torch_dtype:bf16 cache_reuse:256 parallel:8] [] { } {0 0 false false false false false 0 0 false} {<nil> []} {0 map[] [] []} { [] [] 0 0 <nil>} { passthrough 0} {[]} {0 0}} caller={caller.file="/build/core/http/endpoints/openai/image.go" caller.L=124 }
…
Jul 01 20:32:36 INFO BackendLoader starting modelID="chroma1-hd" backend="diffusers" model="lodestones/Chroma1-HD" caller={caller.file="/build/pkg/model/initializers.go" caller.L=222 }
Jul 01 20:32:36 INFO effective runtime tuning (override in the model YAML; LOCALAI_DISABLE_HARDWARE_DEFAULTS=true disables hardware auto-tuning) modelID="chroma1-hd" context=4096 n_batch=512 n_gpu_layers=99999999 parallel="8" flash_attention="auto" f16=false caller={caller.file="/build/pkg/model/initializers.go" caller.L=231 }
Jul 01 20:32:36 DEBUG Loading model in memory from file file="/models/lodestones/Chroma1-HD" caller={caller.file="/build/pkg/model/loader.go" caller.L=388 }
Jul 01 20:32:36 DEBUG Loading Model with gRPC modelID="chroma1-hd" file="/models/lodestones/Chroma1-HD" backend="diffusers" options={diffusers lodestones/Chroma1-HD chroma1-hd 0x984e5a375e0 0x984e4976c08 map[] 20 2 true 45292441526} caller={caller.file="/build/pkg/model/initializers.go" caller.L=56 }
Jul 01 20:32:36 DEBUG Loading external backend uri="/backends/rocm-diffusers/run.sh" caller={caller.file="/build/pkg/model/initializers.go" caller.L=113 }
Jul 01 20:32:36 DEBUG external backend is file file=&{run.sh 410 493 {0 63917722108 0x9627680} {66307 12851355 1 33261 0 0 0 0 410 4096 8 {1782891630 985754836} {1782125308 0} {1782631523 755900323} [0 0 0]}} caller={caller.file="/build/pkg/model/initializers.go" caller.L=116 }
Jul 01 20:32:36 DEBUG Loading GRPC Process process="/backends/rocm-diffusers/run.sh" caller={caller.file="/build/pkg/model/process.go" caller.L=148 }
Jul 01 20:32:36 DEBUG GRPC Service will be running id="chroma1-hd" address="127.0.0.1:34021" caller={caller.file="/build/pkg/model/process.go" caller.L=150 }
Jul 01 20:32:36 DEBUG GRPC Service state dir dir="/tmp/go-processmanager3706345888" caller={caller.file="/build/pkg/model/process.go" caller.L=183 }
Jul 01 20:32:36 DEBUG GRPC Service Started caller={caller.file="/build/pkg/model/initializers.go" caller.L=128 }
Jul 01 20:32:36 DEBUG Wait for the service to start up caller={caller.file="/build/pkg/model/initializers.go" caller.L=141 }
Jul 01 20:32:36 DEBUG Options options=ContextSize:4096 Seed:1955829538 NBatch:512 MMap:true NGPULayers:99999999 Threads:12 PipelineType:"ChromaPipeline" CFGScale:3 FlashAttention:"auto" Options:"torch_dtype:bf16" Options:"cache_reuse:256" Options:"parallel:8" caller={caller.file="/build/pkg/model/initializers.go" caller.L=142 }
Jul 01 20:32:36 DEBUG GRPC stdout id="chroma1-hd-127.0.0.1:34021" line="Initializing libbackend for rocm-diffusers" caller={caller.file="/build/pkg/model/process.go" caller.L=220 }
Jul 01 20:32:36 DEBUG GRPC stdout id="chroma1-hd-127.0.0.1:34021" line="Using portable Python" caller={caller.file="/build/pkg/model/process.go" caller.L=220 }
…
Jul 01 20:32:36 DEBUG GRPC stdout id="chroma1-hd-127.0.0.1:34021" line="Added /backends/rocm-diffusers/lib to LD_LIBRARY_PATH for GPU libraries" caller={caller.file="/build/pkg/model/process.go" caller.L=220 }
…
Jul 01 20:32:39 DEBUG GRPC stderr id="chroma1-hd-127.0.0.1:34021" line="Server started. Listening on: 127.0.0.1:34021" caller={caller.file="/build/pkg/model/process.go" caller.L=207 }
…
Jul 01 20:32:38 DEBUG GRPC stderr id="chroma1-hd-127.0.0.1:34021" line="/backends/rocm-diffusers/venv/lib/python3.10/site-packages/transformers/utils/hub.py:110: FutureWarning: Using `TRANSFORMERS_CACHE` is deprecated and will be removed in v5 of Transformers. Use `HF_HOME` instead." caller={caller.file="/build/pkg/model/process.go" caller.L=207 }
Jul 01 20:32:38 DEBUG GRPC stderr id="chroma1-hd-127.0.0.1:34021" line=" warnings.warn(" caller={caller.file="/build/pkg/model/process.go" caller.L=207 }
…
Jul 01 20:32:40 DEBUG GRPC Service Ready caller={caller.file="/build/pkg/model/initializers.go" caller.L=149 }
Jul 01 20:32:40 DEBUG GRPC: Loading model with options options=Model:"lodestones/Chroma1-HD" ContextSize:4096 Seed:1955829538 NBatch:512 MMap:true NGPULayers:99999999 Threads:12 ModelFile:"/models/lodestones/Chroma1-HD" PipelineType:"ChromaPipeline" CFGScale:3 FlashAttention:"auto" ModelPath:"//models" Options:"torch_dtype:bf16" Options:"cache_reuse:256" Options:"parallel:8" caller={caller.file="/build/pkg/model/initializers.go" caller.L=173 }
Jul 01 20:32:40 DEBUG GRPC stderr id="chroma1-hd-127.0.0.1:34021" line="Loading model lodestones/Chroma1-HD..." caller={caller.file="/build/pkg/model/process.go" caller.L=207 }
Jul 01 20:32:40 DEBUG GRPC stderr id="chroma1-hd-127.0.0.1:34021" line="Request Model: \"lodestones/Chroma1-HD\"" caller={caller.file="/build/pkg/model/process.go" caller.L=207 }
Jul 01 20:32:40 DEBUG GRPC stderr id="chroma1-hd-127.0.0.1:34021" line="ContextSize: 4096" caller={caller.file="/build/pkg/model/process.go" caller.L=207 }
Jul 01 20:32:40 DEBUG GRPC stderr id="chroma1-hd-127.0.0.1:34021" line="Seed: 1955829538" caller={caller.file="/build/pkg/model/process.go" caller.L=207 }
Jul 01 20:32:40 DEBUG GRPC stderr id="chroma1-hd-127.0.0.1:34021" line="NBatch: 512" caller={caller.file="/build/pkg/model/process.go" caller.L=207 }
Jul 01 20:32:40 DEBUG GRPC stderr id="chroma1-hd-127.0.0.1:34021" line="MMap: true" caller={caller.file="/build/pkg/model/process.go" caller.L=207 }
Jul 01 20:32:40 DEBUG GRPC stderr id="chroma1-hd-127.0.0.1:34021" line="NGPULayers: 99999999" caller={caller.file="/build/pkg/model/process.go" caller.L=207 }
Jul 01 20:32:40 DEBUG GRPC stderr id="chroma1-hd-127.0.0.1:34021" line="Threads: 12" caller={caller.file="/build/pkg/model/process.go" caller.L=207 }
Jul 01 20:32:40 DEBUG GRPC stderr id="chroma1-hd-127.0.0.1:34021" line="ModelFile: \"/models/lodestones/Chroma1-HD\"" caller={caller.file="/build/pkg/model/process.go" caller.L=207 }
Jul 01 20:32:40 DEBUG GRPC stderr id="chroma1-hd-127.0.0.1:34021" line="PipelineType: \"ChromaPipeline\"" caller={caller.file="/build/pkg/model/process.go" caller.L=207 }
Jul 01 20:32:40 DEBUG GRPC stderr id="chroma1-hd-127.0.0.1:34021" line="CFGScale: 3" caller={caller.file="/build/pkg/model/process.go" caller.L=207 }
Jul 01 20:32:40 DEBUG GRPC stderr id="chroma1-hd-127.0.0.1:34021" line="FlashAttention: \"auto\"" caller={caller.file="/build/pkg/model/process.go" caller.L=207 }
Jul 01 20:32:40 DEBUG GRPC stderr id="chroma1-hd-127.0.0.1:34021" line="ModelPath: \"//models\"" caller={caller.file="/build/pkg/model/process.go" caller.L=207 }
Jul 01 20:32:40 DEBUG GRPC stderr id="chroma1-hd-127.0.0.1:34021" line="Options: \"torch_dtype:bf16\"" caller={caller.file="/build/pkg/model/process.go" caller.L=207 }
Jul 01 20:32:40 DEBUG GRPC stderr id="chroma1-hd-127.0.0.1:34021" line="Options: \"cache_reuse:256\"" caller={caller.file="/build/pkg/model/process.go" caller.L=207 }
Jul 01 20:32:40 DEBUG GRPC stderr id="chroma1-hd-127.0.0.1:34021" line="Options: \"parallel:8\"" caller={caller.file="/build/pkg/model/process.go" caller.L=207 }
Jul 01 20:32:40 DEBUG GRPC stderr id="chroma1-hd-127.0.0.1:34021" line="" caller={caller.file="/build/pkg/model/process.go" caller.L=207 }
Jul 01 20:32:40 DEBUG GRPC stderr id="chroma1-hd-127.0.0.1:34021" line="Options: {'cache_reuse': 256.0, 'parallel': 8.0}" caller={caller.file="/build/pkg/model/process.go" caller.L=207 }
Jul 01 20:32:40 DEBUG GRPC stderr id="chroma1-hd-127.0.0.1:34021" line="LoadModel: PipelineType from request: ChromaPipeline" caller={caller.file="/build/pkg/model/process.go" caller.L=207 }
…
Jul 01 20:32:40 DEBUG GRPC stderr id="chroma1-hd-127.0.0.1:34021" line="Modular Diffusers is currently an experimental feature under active development. The API is subject to breaking changes in future releases." caller={caller.file="/build/pkg/model/process.go" caller.L=207 }
…
Jul 01 20:33:02 DEBUG GRPC stdout id="chroma1-hd-127.0.0.1:34021" line="Received termination signal. Shutting down..." caller={caller.file="/build/pkg/model/process.go" caller.L=220 }
…
Jul 01 20:32:40 DEBUG GRPC stderr id="chroma1-hd-127.0.0.1:34021" line="Modular Diffusers is currently an experimental feature under active development. The API is subject to breaking changes in future releases." caller={caller.file="/build/pkg/model/process.go" caller.L=207 }
…
Jul 01 20:33:17 ERROR Failed to load model modelID="chroma1-hd" error=failed to load model with internal loader: could not load model: rpc error: code = Canceled desc = context canceled backend="diffusers" caller={caller.file="/build/pkg/model/initializers.go" caller.L=263 }
Jul 01 20:33:17 INFO HTTP request method="POST" path="/v1/images/generations" status=500 caller={caller.file="/build/core/http/app.go" caller.L=217 }
…
Jul 01 20:33:17 WARN Backend process exited unexpectedly id="chroma1-hd" address="127.0.0.1:34021" process="run.sh" exitCode="-1" caller={caller.file="/build/pkg/model/process.go" caller.L=255 }
Additional context
Logs and traces are not helpful in this case.
The model configuration in the example is as downloaded from the gallery:
backend: diffusers
cfg_scale: 3
diffusers:
pipeline_type: ChromaPipeline
known_usecases:
- image
name: chroma1-hd
options:
- torch_dtype:bf16
parameters:
model: lodestones/Chroma1-HD
step: 40
LocalAI version:
localai/localai:latest-gpu-hipblasorlocalai/localai:latest-gpu-vulkan.LocalAI v4.5.6 (02b007a)
Environment, CPU architecture, OS, and Version:
Linux minisforum 7.0.0-27-generic #27-Ubuntu SMP PREEMPT_DYNAMIC Thu Jun 18 19:13:49 UTC 2026 x86_64 GNU/Linux
In UEFI, 48GB out of 96GM RAM is set for frame buffer for AMD iGPU.
docker-compose.yml:Describe the bug
An attempt to generate an image with any model, afre less than a minute, shows an error message: "Error: NetworkError when attempting to fetch resource." (by the way, it is too geneic to be of use).
To Reproduce
On Studio page, try to generate an image from a prompt using an installed Stable diffusion or Diffusers model.
Expected behavior
An image is shown after some time.
Logs
The API trace says: "failed to load model with internal loader: could not load model: rpc error: code = Canceled desc = context canceled" (again, a uselessly generic message),
The backend trace is:
The relevant container log entries are:
Additional context
Logs and traces are not helpful in this case.
The model configuration in the example is as downloaded from the gallery: