All pull requests

Pull requests

• chore(deps): bump body-parser from 1.20.4 to 1.20.9 in demos/embeddings

  #1095·katsugtgz opened Oct 26, 2026Contributor·

  ·
  6

• chore: bump llama.cpp (https://github.com/ggml-org/llama.cpp/releases/b11723)

  dependencies
  #1085·github-actions[bot] opened Oct 19, 2026Bot·

  ·
  8

• feat(vllm): extract tensor_parallel_size and max_model_len from hf_overrides as server flags

  #1083·Ravijangid820 opened Oct 14, 2026·6 tasks done·

  ·
  1

  7

• chore(deps): bump the go-modules-root group across 1 directory with 20 updates

  dependenciesgo
  #1071·dependabot[bot] opened Sep 26, 2026Bot·

  ·
  3

• chore: bump llama.cpp (https://github.com/ggml-org/llama.cpp/releases/b10951)

  dependencies
  #1061·github-actions[bot] opened Sep 14, 2026Bot·

  ·
  5

• chore: bump llama.cpp (https://github.com/ggml-org/llama.cpp/releases/b10830)

  dependencies
  #1057·github-actions[bot] opened Sep 7, 2026Bot·

  ·
  5

• Fix token realm SSRF guard to allow registries on the same host

  #1053·okhowang opened Sep 1, 2026·

  ·
  1

  10

• chore: bump llama.cpp (https://github.com/ggml-org/llama.cpp/releases/b10711)

  dependencies
  #1052·github-actions[bot] opened Aug 31, 2026Bot·

  ·
  5

• docs: document unified memory env configuration

  #1051·amarkdotdev opened Aug 30, 2026·1 task done·

  ·
  1

  11

• chore: bump llama.cpp (https://github.com/ggml-org/llama.cpp/releases/b10603)

  dependencies
  #1047·github-actions[bot] opened Aug 24, 2026Bot·

  ·
  5

• fix(cli): remove unused backend flag from compose up

  #1037·VedantMadane opened Aug 11, 2026Contributor·

  ·
  1

  8

• chore: bump llama.cpp (https://github.com/ggml-org/llama.cpp/releases/b10335)

  dependencies
  #1034·github-actions[bot] opened Aug 10, 2026Bot·

  ·
  5

• chore: bump llama.cpp (https://github.com/ggml-org/llama.cpp/releases/b10236)

  dependencies
  #1030·github-actions[bot] opened Aug 3, 2026Bot·

  ·
  5

• chore: bump llama.cpp (https://github.com/ggml-org/llama.cpp/releases/b10143)

  dependencies
  #1026·github-actions[bot] opened Jul 27, 2026Bot·

  ·
  5

• ci(dmr): sign/notarize via internal repo and publish a Homebrew cask

  #1008·doringeman opened Jul 9, 2026Contributor·

  ·
  8

• [feat] added integration with OpenVINO Model Server

  #940·dtrawins opened May 25, 2026·

  ·
  6

• feat(windows): add Vulkan GPU detection for Intel Arc and other non-CUDA GPUs

  #930·darthcav opened May 21, 2026·3 tasks·

  ·
  1

  25

• Add dmr sandbox config and launch command

  #922·CoderHariswar opened May 19, 2026·

  ·
  1

  49

• docker model runner llmfit launch

  #837·sathiraumesh opened Apr 6, 2026Contributor·

  ·
  1

  13

• feat: implement engine kind detection for default context in context ls

  #823·ilopezluna opened Apr 2, 2026Contributor·

  ·
  19

• feat: add vLLM ROCm variant for AMD GPUs

  #638·doringeman opened Feb 5, 2026Contributor·

  ·
  8

• chore(ci): improve release workflow

  #563·doringeman opened Jan 13, 2026Contributor·

  ·
  5

• Add Windows (CPU) build support

  #476·doringeman opened Dec 4, 2025Contributor·

  ·
  8

• Auto detect MTGPU

  #342·yeahdongcn opened Oct 29, 2025Contributor·

  ·

• fix(llamacpp): correct Docker ARG variable syntax in cann.Dockerfile

  #323·doringeman opened Oct 27, 2025Contributor·

  ·
  5