Skip to content

Actions: serhez/llenvs

Actions

All workflows

Actions

Loading...
Loading

Showing runs from all workflows
149 workflow runs
149 workflow runs

Filter by Workflow

⌥ + click/return to exclude

Filter by Event

⌥ + click/return to exclude

Filter by Status

⌥ + click/return to exclude

Filter by Branch

⌥ + click/return to exclude

Filter by Actor

⌥ + click/return to exclude
feat(inference): add native vllm serve launcher to container backend Deploy docs #147: Commit b8c06ec pushed by serhez
40s main
main
40s
chore(repo): record local docs and OpenApps options Deploy docs #146: Commit 384a566 pushed by serhez
48s main
main
48s
fix(inference): reject unterminated OpenRouter responses Deploy docs #145: Commit f514545 pushed by serhez
43s main
main
43s
fix(inference): fail promptly when owned vLLM service exits Deploy docs #144: Commit d50b4da pushed by serhez
2m 33s main
main
2m 33s
fix(inference): preserve partial continuation scoring results Deploy docs #143: Commit 02a5688 pushed by serhez
37s main
main
37s
fix(openapps): make dataset replay safe and repeatable Deploy docs #142: Commit 54584a8 pushed by serhez
38s main
main
38s
fix(inference): preserve native reasoning for follow-up requests Deploy docs #141: Commit f8e0721 pushed by serhez
33s main
main
33s
fix(inference): normalize body-level input errors Deploy docs #140: Commit 166d2d2 pushed by serhez
35s main
main
35s
fix(inference): reject explicit provider error completions Deploy docs #139: Commit 9df4b5c pushed by serhez
33s main
main
33s
fix(inference): preserve API connection event-loop lifetime Deploy docs #138: Commit 828dbc8 pushed by serhez
34s main
main
34s
fix(alfworld): correct expert selection and refresh reference plans Deploy docs #137: Commit 9f9aae1 pushed by serhez
46s main
main
46s
fix(inference): support pinned host tokenizers for scoring Deploy docs #136: Commit 993afc1 pushed by serhez
39s main
main
39s
fix(frozen-lake): harden action parsing Deploy docs #135: Commit d02f198 pushed by serhez
32s main
main
32s
fix: skip optional adapter registration on any probe failure Deploy docs #134: Commit b46c54a pushed by serhez
40s main
main
40s
fix: honor disable_thinking in SingularityVLLMBackend chat generation Deploy docs #133: Commit 01812b3 pushed by serhez
37s main
main
37s
feat: add continuation scoring to SingularityVLLMBackend Deploy docs #132: Commit e147c20 pushed by serhez
37s main
main
37s
pages build and deployment pages-build-deployment #2: by serhez
23s gh-pages
gh-pages
23s
feat(backends): enable token logprobs on vllm_singularity Deploy docs #131: Commit 856d4c9 pushed by serhez
43s main
main
43s
feat: add Harbor timeout_accounting (exec_only default) charging only… Deploy docs #130: Commit a03e97b pushed by serhez
39s main
main
39s
feat(backends): LiteLLM support Deploy docs #129: Commit a6ab094 pushed by serhez
44s main
main
44s
feat(backends): second elicitation backend wrapper Deploy docs #128: Commit 9646885 pushed by serhez
51s main
main
51s
feat(backends): disable thinking during second elicitation Deploy docs #127: Commit bb8ed69 pushed by serhez
38s main
main
38s
fix(backends): log correct responses from openrouter Deploy docs #126: Commit a38a1c4 pushed by serhez
39s main
main
39s
Merge pull request #3 from serhez/feat/vision-support Deploy docs #125: Commit 6e636e2 pushed by serhez
44s main
main
44s
merging with main changes Deploy docs #124: Commit f922042 pushed by IlzeAmandaA
44s main
main
44s