fix: split prebuilt CUDA binaries into 2 npm modules #918
Triggered via pull request
August 26, 2025 01:11
giladgd
Status
Failure
Total duration
1h 17m 26s
Artifacts
9
build.yml
on: pull_request
Build
2m 5s
Matrix: build-binaries
Update documentation website - no version release
Update documentation website
0s
Auto-approve documentation website deployment
0s
Matrix: build-electron-example
Annotations
5 errors and 4 warnings
|
Model dependent tests
Process completed with exit code 1.
|
|
test/modelDependent/llama3.2/sequenceState.test.ts > llama 3.2 > chatSession > sequence state > restoring to a smaller context sequence fails - 2 sequences:
test/modelDependent/llama3.2/sequenceState.test.ts#L262
Error: Snapshot `llama 3.2 > chatSession > sequence state > restoring to a smaller context sequence fails - 2 sequences 1` mismatched
Expected: ""That's a clever phrase.""
Received: ""That's a clever play on""
❯ test/modelDependent/llama3.2/sequenceState.test.ts:262:33
|
|
test/modelDependent/llama3.2/sequenceState.test.ts > llama 3.2 > chatSession > sequence state > restoring to a smaller context sequence fails:
test/modelDependent/llama3.2/sequenceState.test.ts#L204
Error: Snapshot `llama 3.2 > chatSession > sequence state > restoring to a smaller context sequence fails 1` mismatched
Expected: ""That's a clever phrase.""
Received: ""That's a clever play on""
❯ test/modelDependent/llama3.2/sequenceState.test.ts:204:33
|
|
test/modelDependent/llama3.2/sequenceState.test.ts > llama 3.2 > chatSession > sequence state > save and load a state works across different contexts:
test/modelDependent/llama3.2/sequenceState.test.ts#L143
Error: Snapshot `llama 3.2 > chatSession > sequence state > save and load a state works across different contexts 1` mismatched
Expected: ""That's a clever phrase.""
Received: ""That's a clever play on""
❯ test/modelDependent/llama3.2/sequenceState.test.ts:143:33
|
|
test/modelDependent/llama3.2/sequenceState.test.ts > llama 3.2 > chatSession > sequence state > save and load a state works properly:
test/modelDependent/llama3.2/sequenceState.test.ts#L79
Error: Snapshot `llama 3.2 > chatSession > sequence state > save and load a state works properly 8` mismatched
Expected: ""You didn't tell me to remember anything. This is the""
Received: ""You didn't tell me to remember anything. This conversation just""
❯ test/modelDependent/llama3.2/sequenceState.test.ts:79:35
|
|
Build binaries - Windows (1)
Failed to save: <h2>Our services aren't available right now</h2><p>We're working to restore all services as soon as possible. Please check back soon.</p>0bwqtaAAAAACu6Pu2ROwaS6Qs6cnLb+hQQlkzRURHRTAyMTUARWRnZQ==
|
|
Build binaries - Windows (1)
Failed to restore: Cache service responded with 400
|
|
Model dependent tests
Cache save failed.
|
|
Model dependent tests
Failed to save: Cache size of ~20043 MB (21016662107 B) is over the 10GB limit, not saving cache.
|
Artifacts
Produced during runtime
| Name | Size | Digest | |
|---|---|---|---|
|
bins-linux-1
Expired
|
156 MB |
sha256:d7fd703a9d172ec787826fd28f5d20fde5abde68458fb12ea4c5221804e37b7e
|
|
|
bins-linux-2
Expired
|
73.5 MB |
sha256:21b217519b0b12e21cf2175d0cc84d5d1a67ef7724b4175fa29e2ca1daf64de6
|
|
|
bins-mac-arm64
Expired
|
1.54 MB |
sha256:4ac1136b2aefda9f52ec555741b8db21b6d61df9d42cf514b2ed94af5430d89b
|
|
|
bins-mac-x64
Expired
|
4.11 MB |
sha256:c1816cb10087906f46967f69d827cdc1491e67407986d778e5d961a5ca11e364
|
|
|
bins-win-1
Expired
|
149 MB |
sha256:5d5212eeb621937791abfee593b6be5884f962e2806dd21c6e557f8d1ed7bcd5
|
|
|
bins-win-2
Expired
|
73.7 MB |
sha256:20b6c8dd24e490efc532c1275bc1ae0c8d9aaf82a79190c90feee5804382f288
|
|
|
build
Expired
|
821 KB |
sha256:b8002316ae03dbca8a49eb9b57370d22e901edb374c5842dbf9dd3d22a8596a1
|
|
|
build-templates
Expired
|
32.5 KB |
sha256:cbfa494b758826a65b091e4f54525dceec9dc89022fcf18d73ebeb1641f3268c
|
|
|
llama.cpp
Expired
|
144 MB |
sha256:db9ef4b05f74e8a1715295cc75f521b512bec0c722f3e15d9bbf27b2f92b1b6e
|
|