All pull requests

Pull requests

• [VLM][CB] Roll back pipeline state when generate() throws

  category: continuous batchingcategory: GGUFcategory: LLMcategory: visual language
  #4596·sgonorov opened Oct 6, 2026Contributor·4 tasks done·

  ·
  14

• [JS] Implement EmbeddingPipeline

  category: GH Pages Docscategory: JS API
  #4595·Retribution98 opened Oct 6, 2026Contributor·4 tasks done·

  ·
  4

• Bump the npm-dependencies group across 1 directory with 2 updates

  dependenciesjavascriptno-match-files
  #4593·dependabot[bot] opened Oct 6, 2026Bot·

  ·
  1

  

• Support FunAudioLLM/SenseVoiceSmall model

  category: automatic speech recognitioncategory: CPP APIcategory: GGUFcategory: GH Pages Docscategory: JS APIcategory: Python APIno-match-files
  #4592·byekrang opened Oct 5, 2026Contributor·

  ·
  9

  

• [VLM] Support MiniCPM-V-4.7

  category: GH Pages Docscategory: visual language
  #4591·yatarkan opened Oct 5, 2026Contributor·2 of 4 tasks·

  ·
  17

  

• Add SenseVoice support in WWB.

  category: WWB
  #4590·popovaan opened Oct 5, 2026Contributor·4 tasks·

  ·
  6

  

• Add minicpm v 4 5 video

  category: GGUFcategory: GH Pages Docscategory: visual languagecategory: WWB
  #4589·pavel-esir opened Oct 5, 2026Contributor·3 of 4 tasks·

  ·
  8

  

• Bump the pip-dependencies group across 1 directory with 3 updates

  category: tools_dependenciescategory: WWBdependenciespython
  #4587·dependabot[bot] opened Oct 5, 2026Bot·

  ·
  

• Add tool_call_benchmark to validate tool calling of exported models

  category: GHAno-match-files
  #4584·dhandhalyabhavik opened Oct 3, 2026·

  ·
  133

• Fix stateful (SDPA) batch KV-cache offsets after a request finishes early

  category: GGUFcategory: LLMcategory: visual languageno-match-files
  #4582·10vulture1005 opened Oct 2, 2026·4 tasks done·

  ·
  1

  

• Gemma4 MTM Continuous Batching

  category: cmake / buildcategory: continuous batchingcategory: CPP APIcategory: GGUFcategory: GH Pages Docscategory: GHAcategory: LLMcategory: prompt lookupcategory: Python APIcategory: samplingcategory: speculative decodingcategory: visual languageno-match-files
  #4579·apaniukov opened Oct 2, 2026Contributor·4 tasks·

  ·
  6

• [CB] Query KV cache capacity in tokens and reject requests exceeding it before prefill (#4545)

  category: continuous batchingcategory: CPP APIcategory: LLMcategory: Python APIcategory: visual languageno-match-files
  #4578·uvv-01 opened Oct 2, 2026·4 tasks done·

  ·
  1

  

• [llm_bench][wwb] Remove tiny Qwen3-Omni xfails after checkpoint fix

  category: GGUFcategory: GHAcategory: llm_benchcategory: WWB
  #4575·sgonorov opened Oct 2, 2026Contributor·4 tasks done·

  ·
  16

  

• [GHA] Testing HuggingFace caching proxy

  category: GHAdo_not_mergedo_not_reviewdo-not-merge
  #4574·ababushk opened Oct 2, 2026Contributor·

  ·
  17

• Qwen-Image 2.1 bug fixes

  category: CPP APIcategory: image generationcategory: Python API
  #4573·likholat opened Oct 1, 2026Contributor·Queued·1 of 4 tasks
  14

  

• [EXPERIMENT][WIP] Add k2-fsa/OmniVoice WWB speech-generation wrapper

  category: WWBdo-not-mergeexperimental
  #4568·mlukasze opened Sep 30, 2026Contributor·

  ·
  5

• [TP_GPU] Initial approach to interaction between GenAI and Tensor Parallel plugin

  category: continuous batchingdo-not-mergeno-match-files
  #4567·Lyamin-Roman opened Sep 30, 2026·

  ·
  5

• [Draft] Support CDPruner for qwen3.5

  category: GGUFcategory: visual languagedo_not_reviewdo-not-merge
  #4563·sunxiaoxia2022 opened Sep 30, 2026Contributor·4 tasks·

  ·
  4

• Support LTX2.3 text2video

  category: CPP APIcategory: GGUFcategory: GH Pages Docscategory: GHAcategory: Python APIcategory: Video generation samplescategory: video generation
  #4559·anatyrova opened Sep 30, 2026Contributor·2 of 4 tasks·

  ·
  19

  

• [Video] Add LTX2 Image-to-Video support

  category: cmake / buildcategory: CPP APIcategory: GGUFcategory: GH Pages Docscategory: Python APIcategory: Video generation samplescategory: video generationcategory: WWB
  #4557·goyaladitya05 opened Sep 29, 2026Contributor·4 tasks done·

  ·
  4

• [CI] [GHA] Add missing snapshot_download for some datasets; add SKILL for adding model/dataset downloads

  category: automatic speech recognitioncategory: continuous batchingcategory: GGUFcategory: GHAcategory: tests dependenciesWIP
  #4556·akashchi opened Sep 29, 2026Contributor·3 tasks done·

  ·
  32

  

• [MiniCPM-V-4.7] Add support for WWB and LLM Benchmark

  category: llm_benchcategory: WWB
  #4555·avasenin-14 opened Sep 29, 2026Contributor·2 of 4 tasks·

  ·
  12

• Qwen-Image 2.1 multiple input images support

  category: CPP APIcategory: GGUFcategory: GH Pages Docscategory: Image generation samplescategory: image generationcategory: Python API
  #4550·likholat opened Sep 28, 2026Contributor·3 of 4 tasks·

  ·
  18

  

• Apply GenerationConfig.parsers in VLMPipeline.generate()

  category: GGUFcategory: LLMcategory: visual languageno-match-files
  #4547·goodmai opened Sep 28, 2026Contributor·3 of 4 tasks·

  ·
  1

• Add Qwen3CoderToolParser for the Qwen3-Coder XML tool call format

  category: CPP APIcategory: GGUFcategory: Python APIno-match-files
  #4544·goodmai opened Sep 28, 2026Contributor·3 of 4 tasks·

  ·
  1