github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-08 17:49:24 -05:00
Code Issues 14.6k Packages Projects Releases 122 Wiki Activity

[GH-ISSUE #3297] Do not allow upper-case letters in the model path #64066

New Issue
Closed
opened 2026-05-03 16:02:26 -05:00 by GiteaMirror · 3 comments
GiteaMirror commented 2026-05-03 16:02:26 -05:00
Owner
Copy Link

Originally created by @d3cker on GitHub (Mar 22, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/3297

What is the issue?

Hello community.
I'm using locally hosted Docker repository on Synology NAS. Unfortunately I have an issue with one particular model: wizardcoder-python-13b-v1.0.Q6_K.gguf

$ sha256sum wizardcoder-python-13b-v1.0.Q6_K.gguf
a20f795d17d64e487b6b3446227ba2931bbcb3bc7bb7ebd652b9663efb1f090b  wizardcoder-python-13b-v1.0.Q6_K.gguf

Stored in ollama as:

$ ls -l ~/.ollama/models/blobs/sha256-a20f795d17d64e487b6b3446227ba2931bbcb3bc7bb7ebd652b9663efb1f090b
-rw------- 1 d3cker users 10679148768 mar 22 00:07 .ollama/models/blobs/sha256-a20f795d17d64e487b6b3446227ba2931bbcb3bc7bb7ebd652b9663efb1f090b

Model is accessible so I can run it:

$ ollama run synology:8500/wizardcoder/wizardcoder-python13B:latest 
>>> Hi.
Hello, how can I assist you today? 

>>> Send a message (/? for help)

When I try to push this model to the repository I receive this error:
Client:

$ ollama push synology:8500/wizardcoder/wizardcoder-python13B:latest --insecure
retrieving manifest 
Error: file does not exist

Server (with some extra info printed in upload.go and images.go):

[GIN] 2024/03/22 - 17:15:36 | 200 |      29.936µs |       127.0.0.1 | HEAD     "/"
time=2024-03-22T17:15:36.634+01:00 level=INFO source=images.go:960 msg="error uploading blob: &{application/vnd.ollama.image.model sha256:a20f795d17d64e487b6b3446227ba2931bbcb3bc7bb7ebd652b9663efb1f090b 10679148768  }"
time=2024-03-22T17:15:36.634+01:00 level=INFO source=images.go:961 msg="error uploading blob: {https synology:8500 wizardcoder wizardcoder-python13B latest}"
upload.go: mp.BaseURL: https://synology:8500
upload.go: requestURL: https://synology:8500/v2/wizardcoder/wizardcoder-python13B/blobs/sha256:a20f795d17d64e487b6b3446227ba2931bbcb3bc7bb7ebd652b9663efb1f090b
time=2024-03-22T17:15:36.652+01:00 level=INFO source=images.go:1141 msg="RESP: &{404 Not Found 404 HTTP/1.1 1 1 map[Content-Length:[19] Content-Type:[text/plain; charset=utf-8] Date:[Fri, 22 Mar 2024 16:15:36 GMT] Docker-Distribution-Api-Version:[registry/2.0] X-Content-Type-Options:[nosniff]] {} 19 [] false false map[] 0xc000434480 <nil>}"
upload.go: resp: <nil>
upload.go: err: file does not exist
time=2024-03-22T17:15:36.654+01:00 level=INFO source=images.go:1141 msg="RESP: &{404 Not Found 404 HTTP/1.1 1 1 map[Content-Length:[19] Content-Type:[text/plain; charset=utf-8] Date:[Fri, 22 Mar 2024 16:15:36 GMT] Docker-Distribution-Api-Version:[registry/2.0] X-Content-Type-Options:[nosniff]] 0xc000516540 19 [] false false map[] 0xc00017dc20 <nil>}"
time=2024-03-22T17:15:36.654+01:00 level=INFO source=images.go:963 msg="error uploading blob: file does not exist"
[GIN] 2024/03/22 - 17:15:36 | 200 |   20.234864ms |       127.0.0.1 | POST     "/api/push"

What did you expect to see?

I don't have that issue with other models. For example:
Model: https://huggingface.co/TheBloke/open-llama-3b-v2-wizard-evol-instuct-v2-196k-GGUF/blob/main/open-llama-3b-v2-wizard-evol-instuct-v2-196k.Q8_0.gguf

$ sha256sum open-llama-3b-v2-wizard-evol-instuct-v2-196k.Q8_0.gguf 
07bf92495e6310bc343e116089c5c656caf2e8ee479d30eec2804d5a685cc496  open-llama-3b-v2-wizard-evol-instuct-v2-196k.Q8_0.gguf

Client:

$ ollama push synology:8500/openllama/openllama-3b-v2:latest --insecure
retrieving manifest 
pushing 07bf92495e63... 100% ▕████████████████████████████████████████████████████████████████████████████▏ 3.6 GB                         
pushing d19d7b5ba224... 100% ▕████████████████████████████████████████████████████████████████████████████▏   56 B                         
pushing 6463b496ea44... 100% ▕████████████████████████████████████████████████████████████████████████████▏  146 B                         
pushing c5d3c17f2d37... 100% ▕████████████████████████████████████████████████████████████████████████████▏   40 B                         
pushing fb890504d5eb... 100% ▕████████████████████████████████████████████████████████████████████████████▏  483 B                         
pushing manifest 
success

Server:

[GIN] 2024/03/22 - 17:12:58 | 200 |      42.459µs |       127.0.0.1 | HEAD     "/"
time=2024-03-22T17:12:58.425+01:00 level=INFO source=images.go:960 msg="error uploading blob: &{application/vnd.ollama.image.model sha256:07bf92495e6310bc343e116089c5c656caf2e8ee479d30eec2804d5a685cc496 3641876224  }"
time=2024-03-22T17:12:58.425+01:00 level=INFO source=images.go:961 msg="error uploading blob: {https synology:8500 openllama openllama-3b-v2 latest}"
upload.go: mp.BaseURL: https://synology:8500
upload.go: requestURL: https://synology:8500/v2/openllama/openllama-3b-v2/blobs/sha256:07bf92495e6310bc343e116089c5c656caf2e8ee479d30eec2804d5a685cc496
time=2024-03-22T17:12:58.432+01:00 level=INFO source=images.go:1141 msg="RESP: &{404 Not Found 404 HTTP/1.1 1 1 map[Content-Length:[157] Content-Type:[application/json; charset=utf-8] Date:[Fri, 22 Mar 2024 16:12:58 GMT] Docker-Distribution-Api-Version:[registry/2.0] X-Content-Type-Options:[nosniff]] {} 157 [] false false map[] 0xc00058e480 <nil>}"
upload.go: resp: <nil>
upload.go: err: file does not exist
time=2024-03-22T17:12:58.618+01:00 level=INFO source=images.go:1141 msg="RESP: &{202 Accepted 202 HTTP/1.1 1 1 map[Content-Length:[0] Date:[Fri, 22 Mar 2024 16:12:58 GMT] Docker-Distribution-Api-Version:[registry/2.0] Docker-Upload-Uuid:[da6074c8-9cc1-4e7f-afda-073b7ad82bdb] Location:[http://synology:8500/v2/openllama/openllama-3b-v2/blobs/uploads/da6074c8-9cc1-4e7f-afda-073b7ad82bdb?_state=UV5vI2Bjtem4F0vEIVnIapqAC8hrPQZu4w4GbzhXEY57Ik5hbWUiOiJvcGVubGxhbWEvb3BlbmxsYW1hLTNiLXYyIiwiVVVJRCI6ImRhNjA3NGM4LTljYzEtNGU3Zi1hZmRhLTA3M2I3YWQ4MmJkYiIsIk9mZnNldCI6MCwiU3RhcnRlZEF0IjoiMjAyNC0wMy0yMlQxNjoxMjo1OC4zMzgxNzI1ODJaIn0%3D] Range:[0-0] X-Content-Type-Options:[nosniff]] {} 0 [] false false map[] 0xc00017c5a0 <nil>}"
time=2024-03-22T17:12:58.618+01:00 level=INFO source=upload.go:109 msg="uploading 07bf92495e63 in 37 100 MB part(s)"

Steps to reproduce

  • Deploy registry in a container
$ docker run -d -p 5000:5000 --restart always --name registry registry:2

FROM ./wizardcoder-python-13b-v1.0.Q6_K.gguf


TEMPLATE """{{ .System }}

### Instruction:
{{ .Prompt }}

### Response:
"""

SYSTEM """
Below is an instruction that describes a task. Write a response that appropriately completes the request.
"""

PARAMETER stop "### Instruction:"
PARAMETER stop "### Response:"
  • Create model on ollama server:
$ ollama create localhost:5000/wizardcoder/wizardcoder-python13B:latest --insecure-f Modelfile
  • Push model to local registry:
$ ollama push localhost:5000/wizardcoder/wizardcoder-python13B:latest --insecure

Are there any recent changes that introduced the issue?

I'm not sure if there was any change that introduced the issue. I tried several previous commits and I always end up with the same error.

OS

Linux

Architecture

x86_64

Platform

No response

Ollama version

0.0.0 (commit a5ba0fcf78)

GPU

AMD

GPU info

ROCk module is loaded
=====================    
HSA System Attributes    
=====================    
Runtime Version:         1.1
System Timestamp Freq.:  1000.000000MHz
Sig. Max Wait Duration:  18446744073709551615 (0xFFFFFFFFFFFFFFFF) (timestamp count)
Machine Model:           LARGE                              
System Endianness:       LITTLE                             
Mwaitx:                  DISABLED
DMAbuf Support:          YES

==========               
HSA Agents               
==========               
*******                  
Agent 1                  
*******                  
  Name:                    Intel(R) Core(TM) i9-10940X CPU @ 3.30GHz
  Uuid:                    CPU-XX                             
  Marketing Name:          Intel(R) Core(TM) i9-10940X CPU @ 3.30GHz
  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:                      32768(0x8000) KB                   
  Chip ID:                 0(0x0)                             
  ASIC Revision:           0(0x0)                             
  Cacheline Size:          64(0x40)                           
  Max Clock Freq. (MHz):   4300                               
  BDFID:                   0                                  
  Internal Node ID:        0                                  
  Compute Unit:            28                                 
  SIMDs per CU:            0                                  
  Shader Engines:          0                                  
  Shader Arrs. per Eng.:   0                                  
  WatchPts on Addr. Ranges:1                                  
  Features:                None
  Pool Info:               
    Pool 1                   
      Segment:                 GLOBAL; FLAGS: FINE GRAINED        
      Size:                    65506932(0x3e78e74) KB             
      Allocatable:             TRUE                               
      Alloc Granule:           4KB                                
      Alloc Alignment:         4KB                                
      Accessible by all:       TRUE                               
    Pool 2                   
      Segment:                 GLOBAL; FLAGS: KERNARG, FINE GRAINED
      Size:                    65506932(0x3e78e74) KB             
      Allocatable:             TRUE                               
      Alloc Granule:           4KB                                
      Alloc Alignment:         4KB                                
      Accessible by all:       TRUE                               
    Pool 3                   
      Segment:                 GLOBAL; FLAGS: COARSE GRAINED      
      Size:                    65506932(0x3e78e74) KB             
      Allocatable:             TRUE                               
      Alloc Granule:           4KB                                
      Alloc Alignment:         4KB                                
      Accessible by all:       TRUE                               
  ISA Info:                
*******                  
Agent 2                  
*******                  
  Name:                    gfx1100                            
  Uuid:                    GPU-af532b568c7bef7a               
  Marketing Name:          Radeon RX 7900 XTX                 
  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:                      6144(0x1800) KB                    
    L3:                      98304(0x18000) KB                  
  Chip ID:                 29772(0x744c)                      
  ASIC Revision:           0(0x0)                             
  Cacheline Size:          64(0x40)                           
  Max Clock Freq. (MHz):   2371                               
  BDFID:                   26368                              
  Internal Node ID:        1                                  
  Compute Unit:            96                                 
  SIMDs per CU:            2                                  
  Shader Engines:          6                                  
  Shader Arrs. per Eng.:   2                                  
  WatchPts on Addr. Ranges:4                                  
  Coherent Host Access:    FALSE                              
  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                        4294967295(0xffffffff)             
    y                        4294967295(0xffffffff)             
    z                        4294967295(0xffffffff)             
  Max fbarriers/Workgrp:   32                                 
  Packet Processor uCode:: 550                                
  SDMA engine uCode::      19                                 
  IOMMU Support::          None                               
  Pool Info:               
    Pool 1                   
      Segment:                 GLOBAL; FLAGS: COARSE GRAINED      
      Size:                    25149440(0x17fc000) KB             
      Allocatable:             TRUE                               
      Alloc Granule:           4KB                                
      Alloc Alignment:         4KB                                
      Accessible by all:       FALSE                              
    Pool 2                   
      Segment:                 GLOBAL; FLAGS: EXTENDED FINE GRAINED
      Size:                    25149440(0x17fc000) KB             
      Allocatable:             TRUE                               
      Alloc Granule:           4KB                                
      Alloc Alignment:         4KB                                
      Accessible by all:       FALSE                              
    Pool 3                   
      Segment:                 GROUP                              
      Size:                    64(0x40) KB                        
      Allocatable:             FALSE                              
      Alloc Granule:           0KB                                
      Alloc Alignment:         0KB                                
      Accessible by all:       FALSE                              
  ISA Info:                
    ISA 1                    
      Name:                    amdgcn-amd-amdhsa--gfx1100         
      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                        4294967295(0xffffffff)             
        y                        4294967295(0xffffffff)             
        z                        4294967295(0xffffffff)             
      FBarrier Max Size:       32                                 
*** Done ***

CPU

Intel

Other software

Docker registry from Docker Hub from https://hub.docker.com/_/registry (latest)
Running on ARM based Synology NAS. I also reproduced this issue with registry (b4fd5ad419a22e955f5c05bcdfdfca91125edc3ed09c60b9979f80be954c97d0) running locally on my desktop.

Originally created by @d3cker on GitHub (Mar 22, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/3297 ### What is the issue? Hello community. I'm using locally hosted Docker repository on Synology NAS. Unfortunately I have an issue with one particular model: *wizardcoder-python-13b-v1.0.Q6_K.gguf* ``` $ sha256sum wizardcoder-python-13b-v1.0.Q6_K.gguf a20f795d17d64e487b6b3446227ba2931bbcb3bc7bb7ebd652b9663efb1f090b wizardcoder-python-13b-v1.0.Q6_K.gguf ``` Stored in ollama as: ``` $ ls -l ~/.ollama/models/blobs/sha256-a20f795d17d64e487b6b3446227ba2931bbcb3bc7bb7ebd652b9663efb1f090b -rw------- 1 d3cker users 10679148768 mar 22 00:07 .ollama/models/blobs/sha256-a20f795d17d64e487b6b3446227ba2931bbcb3bc7bb7ebd652b9663efb1f090b ``` Model is accessible so I can run it: ``` $ ollama run synology:8500/wizardcoder/wizardcoder-python13B:latest >>> Hi. Hello, how can I assist you today? >>> Send a message (/? for help) ``` When I try to push this model to the repository I receive this error: Client: ``` $ ollama push synology:8500/wizardcoder/wizardcoder-python13B:latest --insecure retrieving manifest Error: file does not exist ``` Server (with some extra info printed in upload.go and images.go): ``` [GIN] 2024/03/22 - 17:15:36 | 200 | 29.936µs | 127.0.0.1 | HEAD "/" time=2024-03-22T17:15:36.634+01:00 level=INFO source=images.go:960 msg="error uploading blob: &{application/vnd.ollama.image.model sha256:a20f795d17d64e487b6b3446227ba2931bbcb3bc7bb7ebd652b9663efb1f090b 10679148768 }" time=2024-03-22T17:15:36.634+01:00 level=INFO source=images.go:961 msg="error uploading blob: {https synology:8500 wizardcoder wizardcoder-python13B latest}" upload.go: mp.BaseURL: https://synology:8500 upload.go: requestURL: https://synology:8500/v2/wizardcoder/wizardcoder-python13B/blobs/sha256:a20f795d17d64e487b6b3446227ba2931bbcb3bc7bb7ebd652b9663efb1f090b time=2024-03-22T17:15:36.652+01:00 level=INFO source=images.go:1141 msg="RESP: &{404 Not Found 404 HTTP/1.1 1 1 map[Content-Length:[19] Content-Type:[text/plain; charset=utf-8] Date:[Fri, 22 Mar 2024 16:15:36 GMT] Docker-Distribution-Api-Version:[registry/2.0] X-Content-Type-Options:[nosniff]] {} 19 [] false false map[] 0xc000434480 <nil>}" upload.go: resp: <nil> upload.go: err: file does not exist time=2024-03-22T17:15:36.654+01:00 level=INFO source=images.go:1141 msg="RESP: &{404 Not Found 404 HTTP/1.1 1 1 map[Content-Length:[19] Content-Type:[text/plain; charset=utf-8] Date:[Fri, 22 Mar 2024 16:15:36 GMT] Docker-Distribution-Api-Version:[registry/2.0] X-Content-Type-Options:[nosniff]] 0xc000516540 19 [] false false map[] 0xc00017dc20 <nil>}" time=2024-03-22T17:15:36.654+01:00 level=INFO source=images.go:963 msg="error uploading blob: file does not exist" [GIN] 2024/03/22 - 17:15:36 | 200 | 20.234864ms | 127.0.0.1 | POST "/api/push" ``` ### What did you expect to see? I don't have that issue with other models. For example: Model: https://huggingface.co/TheBloke/open-llama-3b-v2-wizard-evol-instuct-v2-196k-GGUF/blob/main/open-llama-3b-v2-wizard-evol-instuct-v2-196k.Q8_0.gguf ``` $ sha256sum open-llama-3b-v2-wizard-evol-instuct-v2-196k.Q8_0.gguf 07bf92495e6310bc343e116089c5c656caf2e8ee479d30eec2804d5a685cc496 open-llama-3b-v2-wizard-evol-instuct-v2-196k.Q8_0.gguf ``` Client: ``` $ ollama push synology:8500/openllama/openllama-3b-v2:latest --insecure retrieving manifest pushing 07bf92495e63... 100% ▕████████████████████████████████████████████████████████████████████████████▏ 3.6 GB pushing d19d7b5ba224... 100% ▕████████████████████████████████████████████████████████████████████████████▏ 56 B pushing 6463b496ea44... 100% ▕████████████████████████████████████████████████████████████████████████████▏ 146 B pushing c5d3c17f2d37... 100% ▕████████████████████████████████████████████████████████████████████████████▏ 40 B pushing fb890504d5eb... 100% ▕████████████████████████████████████████████████████████████████████████████▏ 483 B pushing manifest success ``` Server: ``` [GIN] 2024/03/22 - 17:12:58 | 200 | 42.459µs | 127.0.0.1 | HEAD "/" time=2024-03-22T17:12:58.425+01:00 level=INFO source=images.go:960 msg="error uploading blob: &{application/vnd.ollama.image.model sha256:07bf92495e6310bc343e116089c5c656caf2e8ee479d30eec2804d5a685cc496 3641876224 }" time=2024-03-22T17:12:58.425+01:00 level=INFO source=images.go:961 msg="error uploading blob: {https synology:8500 openllama openllama-3b-v2 latest}" upload.go: mp.BaseURL: https://synology:8500 upload.go: requestURL: https://synology:8500/v2/openllama/openllama-3b-v2/blobs/sha256:07bf92495e6310bc343e116089c5c656caf2e8ee479d30eec2804d5a685cc496 time=2024-03-22T17:12:58.432+01:00 level=INFO source=images.go:1141 msg="RESP: &{404 Not Found 404 HTTP/1.1 1 1 map[Content-Length:[157] Content-Type:[application/json; charset=utf-8] Date:[Fri, 22 Mar 2024 16:12:58 GMT] Docker-Distribution-Api-Version:[registry/2.0] X-Content-Type-Options:[nosniff]] {} 157 [] false false map[] 0xc00058e480 <nil>}" upload.go: resp: <nil> upload.go: err: file does not exist time=2024-03-22T17:12:58.618+01:00 level=INFO source=images.go:1141 msg="RESP: &{202 Accepted 202 HTTP/1.1 1 1 map[Content-Length:[0] Date:[Fri, 22 Mar 2024 16:12:58 GMT] Docker-Distribution-Api-Version:[registry/2.0] Docker-Upload-Uuid:[da6074c8-9cc1-4e7f-afda-073b7ad82bdb] Location:[http://synology:8500/v2/openllama/openllama-3b-v2/blobs/uploads/da6074c8-9cc1-4e7f-afda-073b7ad82bdb?_state=UV5vI2Bjtem4F0vEIVnIapqAC8hrPQZu4w4GbzhXEY57Ik5hbWUiOiJvcGVubGxhbWEvb3BlbmxsYW1hLTNiLXYyIiwiVVVJRCI6ImRhNjA3NGM4LTljYzEtNGU3Zi1hZmRhLTA3M2I3YWQ4MmJkYiIsIk9mZnNldCI6MCwiU3RhcnRlZEF0IjoiMjAyNC0wMy0yMlQxNjoxMjo1OC4zMzgxNzI1ODJaIn0%3D] Range:[0-0] X-Content-Type-Options:[nosniff]] {} 0 [] false false map[] 0xc00017c5a0 <nil>}" time=2024-03-22T17:12:58.618+01:00 level=INFO source=upload.go:109 msg="uploading 07bf92495e63 in 37 100 MB part(s)" ``` ### Steps to reproduce - Deploy registry in a container ``` $ docker run -d -p 5000:5000 --restart always --name registry registry:2 ``` - Download model from https://huggingface.co/TheBloke/WizardCoder-Python-13B-V1.0-GGUF/blob/main/wizardcoder-python-13b-v1.0.Q6_K.gguf - Create Modelfile: ``` FROM ./wizardcoder-python-13b-v1.0.Q6_K.gguf TEMPLATE """{{ .System }} ### Instruction: {{ .Prompt }} ### Response: """ SYSTEM """ Below is an instruction that describes a task. Write a response that appropriately completes the request. """ PARAMETER stop "### Instruction:" PARAMETER stop "### Response:" ``` - Create model on ollama server: ``` $ ollama create localhost:5000/wizardcoder/wizardcoder-python13B:latest --insecure-f Modelfile ``` - Push model to local registry: ``` $ ollama push localhost:5000/wizardcoder/wizardcoder-python13B:latest --insecure ``` ### Are there any recent changes that introduced the issue? I'm not sure if there was any change that introduced the issue. I tried several previous commits and I always end up with the same error. ### OS Linux ### Architecture x86_64 ### Platform _No response_ ### Ollama version 0.0.0 (commit a5ba0fcf788a3d7543e2011593670ddc5012f125) ### GPU AMD ### GPU info ``` ROCk module is loaded ===================== HSA System Attributes ===================== Runtime Version: 1.1 System Timestamp Freq.: 1000.000000MHz Sig. Max Wait Duration: 18446744073709551615 (0xFFFFFFFFFFFFFFFF) (timestamp count) Machine Model: LARGE System Endianness: LITTLE Mwaitx: DISABLED DMAbuf Support: YES ========== HSA Agents ========== ******* Agent 1 ******* Name: Intel(R) Core(TM) i9-10940X CPU @ 3.30GHz Uuid: CPU-XX Marketing Name: Intel(R) Core(TM) i9-10940X CPU @ 3.30GHz 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: 32768(0x8000) KB Chip ID: 0(0x0) ASIC Revision: 0(0x0) Cacheline Size: 64(0x40) Max Clock Freq. (MHz): 4300 BDFID: 0 Internal Node ID: 0 Compute Unit: 28 SIMDs per CU: 0 Shader Engines: 0 Shader Arrs. per Eng.: 0 WatchPts on Addr. Ranges:1 Features: None Pool Info: Pool 1 Segment: GLOBAL; FLAGS: FINE GRAINED Size: 65506932(0x3e78e74) KB Allocatable: TRUE Alloc Granule: 4KB Alloc Alignment: 4KB Accessible by all: TRUE Pool 2 Segment: GLOBAL; FLAGS: KERNARG, FINE GRAINED Size: 65506932(0x3e78e74) KB Allocatable: TRUE Alloc Granule: 4KB Alloc Alignment: 4KB Accessible by all: TRUE Pool 3 Segment: GLOBAL; FLAGS: COARSE GRAINED Size: 65506932(0x3e78e74) KB Allocatable: TRUE Alloc Granule: 4KB Alloc Alignment: 4KB Accessible by all: TRUE ISA Info: ******* Agent 2 ******* Name: gfx1100 Uuid: GPU-af532b568c7bef7a Marketing Name: Radeon RX 7900 XTX 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: 6144(0x1800) KB L3: 98304(0x18000) KB Chip ID: 29772(0x744c) ASIC Revision: 0(0x0) Cacheline Size: 64(0x40) Max Clock Freq. (MHz): 2371 BDFID: 26368 Internal Node ID: 1 Compute Unit: 96 SIMDs per CU: 2 Shader Engines: 6 Shader Arrs. per Eng.: 2 WatchPts on Addr. Ranges:4 Coherent Host Access: FALSE 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 4294967295(0xffffffff) y 4294967295(0xffffffff) z 4294967295(0xffffffff) Max fbarriers/Workgrp: 32 Packet Processor uCode:: 550 SDMA engine uCode:: 19 IOMMU Support:: None Pool Info: Pool 1 Segment: GLOBAL; FLAGS: COARSE GRAINED Size: 25149440(0x17fc000) KB Allocatable: TRUE Alloc Granule: 4KB Alloc Alignment: 4KB Accessible by all: FALSE Pool 2 Segment: GLOBAL; FLAGS: EXTENDED FINE GRAINED Size: 25149440(0x17fc000) KB Allocatable: TRUE Alloc Granule: 4KB Alloc Alignment: 4KB Accessible by all: FALSE Pool 3 Segment: GROUP Size: 64(0x40) KB Allocatable: FALSE Alloc Granule: 0KB Alloc Alignment: 0KB Accessible by all: FALSE ISA Info: ISA 1 Name: amdgcn-amd-amdhsa--gfx1100 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 4294967295(0xffffffff) y 4294967295(0xffffffff) z 4294967295(0xffffffff) FBarrier Max Size: 32 *** Done *** ``` ### CPU Intel ### Other software Docker registry from Docker Hub from https://hub.docker.com/_/registry (latest) Running on ARM based Synology NAS. I also reproduced this issue with registry (b4fd5ad419a22e955f5c05bcdfdfca91125edc3ed09c60b9979f80be954c97d0) running locally on my desktop.
GiteaMirror added the bugfeature request labels 2026-05-03 16:02:28 -05:00
GiteaMirror commented 2026-05-03 16:03:17 -05:00
Author
Owner
Copy Link

@d3cker commented on GitHub (Mar 22, 2024):

I forgot that Docker allows only lowercase letters in PATH. Uppercase letters are allowed in TAG. See Documentation. After changing the name, everything started working as expected:

$ ollama cp synology:8500/wizardcoder/wizardcoder-python13B synology:8500/wizardcoder/wizardcoder-python13bq6
copied 'synology:8500/wizardcoder/wizardcoder-python13B' to 'synology:8500/wizardcoder/wizardcoder-python13bq6'
$ ollama push synology:8500/wizardcoder/wizardcoder-python13bq6 --insecure
retrieving manifest 
pushing a20f795d17d6... 100% ▕████████████████████████████████████████████████████████████████████████████▏  10 GB                         
pushing 2d836d77287d... 100% ▕████████████████████████████████████████████████████████████████████████████▏   61 B                         
pushing 85c1d23a20f1... 100% ▕████████████████████████████████████████████████████████████████████████████▏  107 B                         
pushing ec393ee2f942... 100% ▕████████████████████████████████████████████████████████████████████████████▏   46 B                         
pushing 89fa79a044b4... 100% ▕████████████████████████████████████████████████████████████████████████████▏  484 B                         
pushing manifest 
success

In other words, this is not a bug, but rather room for improvement. Maybe it's worth imposing this naming convention in the image creation process. For example (server/modelpath.go):

--- modelpath.go	2024-03-22 21:56:54.972428019 +0100
+++ modelpath.go.patched	2024-03-22 21:58:05.887662569 +0100
@@ -45,23 +45,26 @@
 		name = after
 	}
 
+	repository := ""
 	name = strings.ReplaceAll(name, string(os.PathSeparator), "/")
 	parts := strings.Split(name, "/")
 	switch len(parts) {
 	case 3:
 		mp.Registry = parts[0]
-		mp.Namespace = parts[1]
-		mp.Repository = parts[2]
+		mp.Namespace = strings.ToLower(parts[1])
+		repository = parts[2]
 	case 2:
 		mp.Namespace = parts[0]
-		mp.Repository = parts[1]
+		repository = parts[1]
 	case 1:
-		mp.Repository = parts[0]
+		repository = parts[0]
 	}
 
-	if repo, tag, found := strings.Cut(mp.Repository, ":"); found {
-		mp.Repository = repo
+	if repo, tag, found := strings.Cut(repository, ":"); found {
+		mp.Repository = strings.ToLower(repo)
 		mp.Tag = tag
+	} else {
+		mp.Repository = strings.ToLower(repository)
 	}
 
 	return mp
<!-- gh-comment-id:2015849813 --> @d3cker commented on GitHub (Mar 22, 2024): I forgot that Docker allows only lowercase letters in `PATH`. Uppercase letters are allowed in `TAG`. See [Documentation](https://docs.docker.com/reference/cli/docker/image/tag/#extended-description). After changing the name, everything started working as expected: ``` $ ollama cp synology:8500/wizardcoder/wizardcoder-python13B synology:8500/wizardcoder/wizardcoder-python13bq6 copied 'synology:8500/wizardcoder/wizardcoder-python13B' to 'synology:8500/wizardcoder/wizardcoder-python13bq6' $ ollama push synology:8500/wizardcoder/wizardcoder-python13bq6 --insecure retrieving manifest pushing a20f795d17d6... 100% ▕████████████████████████████████████████████████████████████████████████████▏ 10 GB pushing 2d836d77287d... 100% ▕████████████████████████████████████████████████████████████████████████████▏ 61 B pushing 85c1d23a20f1... 100% ▕████████████████████████████████████████████████████████████████████████████▏ 107 B pushing ec393ee2f942... 100% ▕████████████████████████████████████████████████████████████████████████████▏ 46 B pushing 89fa79a044b4... 100% ▕████████████████████████████████████████████████████████████████████████████▏ 484 B pushing manifest success ``` In other words, this is not a bug, but rather room for improvement. Maybe it's worth imposing this naming convention in the image creation process. For example (server/modelpath.go): ``` --- modelpath.go 2024-03-22 21:56:54.972428019 +0100 +++ modelpath.go.patched 2024-03-22 21:58:05.887662569 +0100 @@ -45,23 +45,26 @@ name = after } + repository := "" name = strings.ReplaceAll(name, string(os.PathSeparator), "/") parts := strings.Split(name, "/") switch len(parts) { case 3: mp.Registry = parts[0] - mp.Namespace = parts[1] - mp.Repository = parts[2] + mp.Namespace = strings.ToLower(parts[1]) + repository = parts[2] case 2: mp.Namespace = parts[0] - mp.Repository = parts[1] + repository = parts[1] case 1: - mp.Repository = parts[0] + repository = parts[0] } - if repo, tag, found := strings.Cut(mp.Repository, ":"); found { - mp.Repository = repo + if repo, tag, found := strings.Cut(repository, ":"); found { + mp.Repository = strings.ToLower(repo) mp.Tag = tag + } else { + mp.Repository = strings.ToLower(repository) } return mp ```
GiteaMirror commented 2026-05-03 16:03:18 -05:00
Author
Owner
Copy Link

@BruceMacD commented on GitHub (Mar 25, 2024):

Thanks for following up with the details @d3cker, I've updated the title accordingly.

<!-- gh-comment-id:2018560845 --> @BruceMacD commented on GitHub (Mar 25, 2024): Thanks for following up with the details @d3cker, I've updated the title accordingly.
GiteaMirror commented 2026-05-03 16:03:18 -05:00
Author
Owner
Copy Link

@jmorganca commented on GitHub (Apr 21, 2024):

Merging this with #3501

<!-- gh-comment-id:2067830563 --> @jmorganca commented on GitHub (Apr 21, 2024): Merging this with #3501
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 feature request
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#64066
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?