v0.4.3
atlasia-ma/MoulSotv0.4.3Oct 11, 2026by github-actions[bot]
Upgrading?
AI Summary
Aligns the TypeScript SDK with HTTP responses and introduces tournament selection capabilities for large choice sets.
Key Highlights
- Align TypeScript confidence contract with HTTP responses
- Add tournament selection for large choice sets
- Port cached embedder to TypeScript SDK
- Export `jev_confidence` formula
New Features
- Tournament selection for large choice sets
- Cached embedder in TypeScript SDK
- Export `jev_confidence`
Full Release Notes
## What's Changed * fix(sdk): align TypeScript confidence contract with HTTP responses by @debjyotikm in https://github.com/NandhaKishorM/laya/pull/1072 * feat(serve): answer large choices by elimination behind LAYA_TOURNAMENT_GROUP (#302) by @kmitul in https://github.com/NandhaKishorM/laya/pull/1073 * fix(verify): isolate the soak concurrency burst in a helper process by @aashish254 in https://github.com/NandhaKishorM/laya/pull/1074 * chore(deps): bump actions/checkout from 4.4.0 to 7.0.1 by @dependabot[bot] in https://github.com/NandhaKishorM/laya/pull/1075 * chore(deps): bump actions/setup-python from 5.6.0 to 7.0.0 by @dependabot[bot] in https://github.com/NandhaKishorM/laya/pull/1076 * chore(deps-dev): bump @types/node from 26.6.3 to 26.6.4 in /laya-ts by @dependabot[bot] in https://github.com/NandhaKishorM/laya/pull/1078 * chore(deps): bump ruff from 0.16.9 to 0.16.10 by @dependabot[bot] in https://github.com/NandhaKishorM/laya/pull/1079 * chore(deps): bump actions/setup-node from 7.0.0 to 7.1.0 by @dependabot[bot] in https://github.com/NandhaKishorM/laya/pull/1080 * chore(deps): bump actions/upload-artifact from 4.6.2 to 7.0.2 by @dependabot[bot] in https://github.com/NandhaKishorM/laya/pull/1081 * chore(deps): bump actions/download-artifact from 8.0.1 to 8.0.2 by @dependabot[bot] in https://github.com/NandhaKishorM/laya/pull/1082 * docs(guardrails): the #781 page and suite must report only what #781 measured by @aashish254 in https://github.com/NandhaKishorM/laya/pull/1084 * fix(serve): the LAYA_DEFAULT_MODEL default column said english by @aashish254 in https://github.com/NandhaKishorM/laya/pull/1085 * docs(readme): /predict/batch copies one budget to every state by @aashish254 in https://github.com/NandhaKishorM/laya/pull/1086 * ci(java): remeasure model-free test floors on merged main by @Bruce-Yii in https://github.com/NandhaKishorM/laya/pull/1090 * fix(mcp): report a dropped option_order instead of refusing the call by @Bruce-Yii in https://github.com/NandhaKishorM/laya/pull/1091 * fix(examples): the demo server pinned the routing fallback to english by @aashish254 in https://github.com/NandhaKishorM/laya/pull/1092 * docs(routing): the mixed-batch guide omitted the two per-request token budgets by @aashish254 in https://github.com/NandhaKishorM/laya/pull/1093 * docs(finetune): table the three laya-train flags no page documented by @aashish254 in https://github.com/NandhaKishorM/laya/pull/1094 * test(docs): make prose citations into symbols, and check that they resolve by @aashish254 in https://github.com/NandhaKishorM/laya/pull/1095 * test(benchmarks): check the published headline cells against the T4 run by @aashish254 in https://github.com/NandhaKishorM/laya/pull/1096 * docs: correct default-model guidance in deployment surfaces by @Bruce-Yii in https://github.com/NandhaKishorM/laya/pull/1097 * docs(readme): the abstention cut is not option-count invariant, and the map is the fix by @aashish254 in https://github.com/NandhaKishorM/laya/pull/1098 * docs(citations): five prose citations that named no symbol, three pointing elsewhere by @aashish254 in https://github.com/NandhaKishorM/laya/pull/1099 * docs(evals): retire a comment describing thresholds the module deleted by @aashish254 in https://github.com/NandhaKishorM/laya/pull/1101 * test(packaging): bind CONTRIBUTING.md's suite section to the shared list by @aashish254 in https://github.com/NandhaKishorM/laya/pull/1103 * fix(shortlist): the cache dimensionality guard reads under the lock by @aashish254 in https://github.com/NandhaKishorM/laya/pull/1104 * fix(mcp): align model schema nullability by @Ha1baraA11 in https://github.com/NandhaKishorM/laya/pull/1105 * fix(laya-ts): match min_confidence bucket-key error text to Python and Java (#1100) by @bhargavmehta01 in https://github.com/NandhaKishorM/laya/pull/1106 * feat(ts): add tournament selection for large choice sets by @xinpingzh in https://github.com/NandhaKishorM/laya/pull/1108 * fix(calibrate): a falsy non-object temperature_by_options is a refused shape by @aashish254 in https://github.com/NandhaKishorM/laya/pull/1109 * fix(cli): disambiguate bare question id 'questions' from wrapper object (#1110) by @Sarthak-Pandey in https://github.com/NandhaKishorM/laya/pull/1113 * feat(ts): port cached embedder to TypeScript SDK by @Swatantra-66 in https://github.com/NandhaKishorM/laya/pull/1117 * feat(confidence): export jev_confidence, the formula behind the served x_jev_confidence by @aashish254 in https://github.com/NandhaKishorM/laya/pull/1083 ## New Contributors * @bhargavmehta01 made their first contribution in https://github.com/NandhaKishorM/laya/pull/1106 **Full Changelog**: https://github.com/NandhaKishorM/laya/compare/v0.4.2...v0.4.3
Related Repositories
rasbt/LLMs-from-scratch★ 107,086
Implement a ChatGPT-like LLM in PyTorch from scratch, step by step
lyogavin/airllm★ 40,239
AirLLM 2.8T LLM inference with single 4GB GPU
NirDiamant/RAG_Techniques★ 29,962
This repository showcases various advanced techniques for Retrieval-Augmented Generation (RAG) systems. Each technique has a detailed notebook tutorial.
microsoft/OmniParser★ 25,540
A simple screen parsing tool towards pure vision based GUI agent
karpathy/nn-zero-to-hero★ 24,908
Neural Networks: Zero to Hero