Skip to content

Paddler 5.0: completions, embeddings and decisions from one loaded model, kev decisions and TypeSafe compatibility - #270

Merged
mcharytoniuk merged 134 commits into
mainfrom
inference-modes
Oct 30, 2026
Merged

mcharytoniuk merged 134 commits into
mainfrom
inference-modes

Conversation

@mcharytoniuk

@mcharytoniuk mcharytoniuk commented Oct 7, 2026 •

Copy link
Copy Markdown
Contributor

One inference mode per cluster, kev decisions and TypeSafe compatibility.

… desired state PUT once the balancer shuts down
…and servers with real ones or direct checks of the real handlers
…d escape control-token lookalikes the way kev does
…every state change a single owner, cancel replaced downloads, detect dead peers, and make the Makefile portable
…ser cache, and test startup from the stored state, PUT ordering, untouched missing state files, and stuck pipelines
…tead of hand-rolled panics in tests, and share fixtures for agent controllers and generated text
… so multimodal prompts are tokenized only once
…em One requests, keep text.format schemas as raw JSON, compute OpenAI failure statuses once, and subscribe to agent availability before the first scan
…s, and test that new desired states preempt retries and that unread clients release agent slots
…trust the agent's softmax instead of normalizing again
… keep distinct embedding contents in a named struct, and expect Responses usage and text instead of panicking by hand
…k is classified once and its ingestion cannot fail
…late and assert exact dispatch per inference mode
…r seams and test that each refuses the generation
…eachable management address, and list the suites the Makefile actually has in the test skills
…t call them, build test generations through the production preparer, and cap batch sizes with BatchSize::at_most
…alancers that vanish under an agent socket, route a decision refusal through Cluster::decide, and serialize forged notifications in the tests that send them
…serializer, and media marker with failing stand-ins
…NT, and report a Hugging Face client that cannot start
… bodies, a startup-built model resolver and llama-cpp-bindings 0.23
…ambiguous names, and drop leftover dependency declarations
…end TypeSafe a rejection the newer SDK still forwards
…b 1, minijinja 3, reqwest 0.13 and the other new APIs
…e pre-cancelled resolution test after what it checks
…ointer head is configured, read decision hidden states on any model, convert kev checkpoints generically including kev-27b, and adopt llama-cpp-bindings 0.25
…d relative pointer head paths, and return test helpers to expect-based form
…s are tested, leaving KevCheckpoint infallible
@mcharytoniuk
mcharytoniuk marked this pull request as ready for review October 30, 2026 04:20
@mcharytoniuk
mcharytoniuk requested review from a team as code owners October 30, 2026 04:20
@mcharytoniuk
mcharytoniuk merged commit b90cdaa into main Oct 30, 2026
33 checks passed
@mcharytoniuk
mcharytoniuk deleted the inference-modes branch October 30, 2026 04:20
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant