Skip to content

Actions: ModelCloud/Evalution

Actions

All workflows

Actions

Loading...
Loading

Showing runs from all workflows
1,159 workflow runs
1,159 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
Fix llama.cpp chat token ID parity (#143) Release #616: Commit 8cbed6e pushed by Qubitium
27s main
main
27s
perf(llama-cpp): batch distinct scoring prefixes Release #615: Commit 1a7b4da pushed by Qubitium
24s fix/llamacpp-chat-token-ids
fix/llamacpp-chat-token-ids
24s
perf(llama-cpp): reuse shared multiple-choice prefixes Release #614: Commit 570d6bc pushed by Qubitium
24s fix/llamacpp-chat-token-ids
fix/llamacpp-chat-token-ids
24s
fix(llama-cpp): preserve rendered chat token ids Release #613: Commit b1b5728 pushed by Qubitium
22s fix/llamacpp-chat-token-ids
fix/llamacpp-chat-token-ids
22s
Automatically optimize transformer loglikelihood scoring (#142) Release #612: Commit 91bef40 pushed by Qubitium
20s v0.0.17
v0.0.17
20s
Evalution v0.0.17 Release #611: Release v0.0.17 published by Qubitium
28s
28s
Graph Update: pip in /. #1547744898 Dependency Graph #14: by dependabot Bot
44s main
main
44s
Automatically optimize transformer loglikelihood scoring (#142) Release #610: Commit 91bef40 pushed by Qubitium
20s main
main
20s
Remove obsolete cache batch-size helper Release #609: Commit 3219460 pushed by Qubitium
22s codex/buffer-loglikelihood-d2h
codex/buffer-loglikelihood-d2h
22s
Harden automatic prefix cache fallback Release #608: Commit d13c302 pushed by Qubitium
20s codex/buffer-loglikelihood-d2h
codex/buffer-loglikelihood-d2h
20s
Enable prefix caching across transformer loglikelihood Release #607: Commit bd8ba27 pushed by Qubitium
17s codex/buffer-loglikelihood-d2h
codex/buffer-loglikelihood-d2h
17s
Batch prefix prewarm and release completed groups Release #606: Commit 0c74736 pushed by Qubitium
18s codex/buffer-loglikelihood-d2h
codex/buffer-loglikelihood-d2h
18s
Keep Evalution one patch above latest PyPI Release #605: Commit 042b1ef pushed by Qubitium
25s codex/buffer-loglikelihood-d2h
codex/buffer-loglikelihood-d2h
25s
Enable prefix prewarm by default Release #604: Commit 2cbda35 pushed by Qubitium
24s codex/buffer-loglikelihood-d2h
codex/buffer-loglikelihood-d2h
24s
Prewarm shared loglikelihood prefixes Release #603: Commit c52a5cf pushed by Qubitium
20s codex/buffer-loglikelihood-d2h
codex/buffer-loglikelihood-d2h
20s
Add opt-in loglikelihood prefix KV cache Release #602: Commit 065679d pushed by Qubitium
26s codex/buffer-loglikelihood-d2h
codex/buffer-loglikelihood-d2h
26s
Deduplicate repeated one-token loglikelihood prefixes Release #601: Commit bfda845 pushed by Qubitium
19s codex/buffer-loglikelihood-d2h
codex/buffer-loglikelihood-d2h
19s
Bump Evalution version to 0.0.17 Release #600: Commit d966bee pushed by Qubitium
17s codex/buffer-loglikelihood-d2h
codex/buffer-loglikelihood-d2h
17s
Buffer transformer loglikelihood D2H reductions Release #599: Commit df07188 pushed by Qubitium
22s codex/buffer-loglikelihood-d2h
codex/buffer-loglikelihood-d2h
22s
feat: expose transformer graph and compile tuning Release #598: Commit 23e9f43 pushed by Qubitium
20s codex/zml-engine
codex/zml-engine
20s
Evalution v0.0.16 Release #597: Release v0.0.16 published by Qubitium
23s
23s
Bump version from 0.0.15 to 0.0.16 Release #596: Commit b2b8fdc pushed by Qubitium
22s v0.0.16
v0.0.16
22s
Graph Update: pip in /. #1545476137 Dependency Graph #13: by dependabot Bot
44s main
main
44s
Bump version from 0.0.15 to 0.0.16 Release #595: Commit b2b8fdc pushed by Qubitium
24s main
main
24s
Graph Update: pip in /. #1545476033 Dependency Graph #12: by dependabot Bot
42s main
main
42s