All pull requests

Pull requests

• Qualify native speculative tool calling

  #1307·Sayan Shaw (sayanshaw24) opened Nov 8, 2026Contributor·

  ·
  1

• No longer override generic GPU models to CUDA

  #1306·bmehta001 opened Nov 7, 2026Contributor·

  ·
  1

  2

  

• Update vcpkg and telemetry to 3.10.309.1; isolate Apple delegate

  #1305·bmehta001 opened Nov 7, 2026Contributor·

  ·
  5

  

• Share tool-call batch validation and JSON grammar

  #1302·Baiju Meswani (baijumeswani) opened Nov 6, 2026Collaborator·1/2·

  ·
  4

• Add custom model HTTP transport foundation

  #1301·Ayman Bagabas (aymanbagabas) opened Nov 6, 2026Member·

  ·
  3

• Use native Qwen tool continuations

  #1296·Sayan Shaw (sayanshaw24) opened Nov 5, 2026Contributor·

  ·
  29

• Add GPU total-VRAM compatibility filtering to the native model catalog

  #1295·Selena Yang (selenayang888) opened Nov 5, 2026Contributor·

  ·
  5

• SDK v2: expose HTTP activity snapshots and atomic idle stop

  #1290·bmehta001 opened Nov 4, 2026Contributor·

  ·
  3

• Preserve tool-call validation errors when guided recovery fails

  #1282·bmehta001 opened Nov 4, 2026Contributor·

  ·
  1

  2

  

• Add on-device text-to-speech (text-to-speech) on the ORT GenAI VibeVoice model type

  #1271·Aymen (aymenfurter) opened Nov 1, 2026·

  ·
  14

• Bump the npm_and_yarn group across 2 directories with 3 updates

  dependenciesjavascript
  #1269·dependabot[bot] opened Oct 31, 2026Bot·

  ·
  8

• Add versioned cross-stack tool-calling qualification

  #1246·Sayan Shaw (sayanshaw24) opened Oct 26, 2026Contributor·

  ·
  13

• Expose SDK AudioModes for explicit audio workflow selection

  #1235·Mason Corey (themason2011) opened Oct 23, 2026Contributor·

  ·
  4

• Delegate detailed hardware and resource telemetry to GenAI

  #1229·bmehta001 opened Oct 22, 2026Contributor·

  ·
  2

• Add JavaScript ranking and decision sessions

  #1168·Akshay Sonawane (apsonawane) opened Oct 1, 2026Contributor·

  ·
  17

• Add Java ranking and decision sessions

  #1167·Akshay Sonawane (apsonawane) opened Oct 1, 2026Contributor·

  ·
  7

• Add C# ranking and decision sessions

  #1166·Akshay Sonawane (apsonawane) opened Oct 1, 2026Contributor·2/2·

  ·
  29

• Whisper segment timestamps

  #1148·Joel Stidley (joelst) opened Sep 25, 2026·

  ·
  24

• Reclaim cached GenAI CUDA resources after the last CUDA model unloads

  #1110·aciddelgado opened Sep 15, 2026·

  ·
  7

• Add model package support for sdkv2

  #981·Xiaoyu Z (xiaoyu-work) opened Aug 11, 2026Member·

  ·
  29

• Add Harmony (GPT-OSS) Tool Calling Support in FL

  #973·Sayan Shaw (sayanshaw24) opened Aug 10, 2026Contributor·2/2·

  ·
  11

• fix(android cpp): Versioned GenAI Android AAR cache to avoid old cache

  #960·sheetalarkadam opened Aug 7, 2026Contributor·1/2·

  ·
  6

• ci(sdk_v2): build the C++ core for Android in the native pipeline

  #954·sheetalarkadam opened Aug 6, 2026Contributor·2/2·

  ·
  1

• Resolve latest cli-preview release for website CLI download links (#924)

  #938·jennyf19 opened Jul 31, 2026Contributor·

  ·
  1

  4

• Tolerate malformed tool calls in Python SDK chat parsing (fixes #864)

  #872·Justin Chu (justinchuby) opened Jul 12, 2026Contributor·

  ·
  1

  7