Issues

• Eval bug: Gemma4 fails with NotImplemented: map: filter-mapping not implemented

  enhancementgood first issue
  ggml-org/llama.cpp#21547 · Filter by author fischercer opened on Apr 7, 2026
  11

• Feature Request: Graceful reasoning budget termination. Avoid mid-sentence cutoff.

  enhancementgood first issuehelp wanted
  Feature

  ggml-org/llama.cpp#20632 · Filter by author CleStil opened on Mar 16, 2026 · UI: Agentic UX Improvements
  11

  

• Eval bug: wrong default threads in llama-bench

  good first issuelow severityperformance
  ggml-org/llama.cpp#17611 · Filter by author GermanAizek opened on Nov 30, 2025
  13

• GGUF convert support for Vibevoice

  3rd partyenhancementgood first issuehelp wantedmodeltts
  Feature

  ggml-org/llama.cpp#17488 · Filter by author amin-jhn opened on Nov 25, 2025
  6

• Feature Request: Implement missing ops from backends

  enhancementgood first issue
  ggml-org/llama.cpp#14909 · Filter by author am17an opened on Jul 28, 2025
  55

• tutorials : list for llama.cpp

  good first issuehelp wantedroadmap
  ggml-org/llama.cpp#13523 · Filter by author ggerganov opened on May 14, 2025
  24

• tts : add support for Orpheus

  good first issuetts
  ggml-org/llama.cpp#12476 · Filter by author ggerganov opened on Mar 20, 2025
  10

• Compile bug: ios swift xcode build error when upgrade to llama : use cmake for swift build

  buildgood first issuehelp wanted
  ggml-org/llama.cpp#10747 · Filter by author jiabochao opened on Dec 10, 2024
  41

• Misc. bug: server provides strutured output for response_format: json_object, but not for response_format: json_schema

  enhancementgood first issue
  ggml-org/llama.cpp#10732 · Filter by author andysalerno opened on Dec 9, 2024
  8

• Feature Request: llama-server hot swapping cvectors via API like we can do with LoRA adapters now

  enhancementgood first issue
  ggml-org/llama.cpp#10685 · Filter by author gghfez opened on Dec 6, 2024
  4

• llama cpp server cant open to public

  enhancementgood first issueserver
  ggml-org/llama.cpp#6268 · Filter by author Kev1ntan opened on Mar 24, 2024
  8

• split: allow --split-max-size option

  enhancementgood first issuehelp wantedsplit
  ggml-org/llama.cpp#6259 · Filter by author phymbert opened on Mar 23, 2024
  4

• server : add "token healing" support

  enhancementgood first issueroadmap
  ggml-org/llama.cpp#5765 · Filter by author CyberShadow opened on Feb 28, 2024
  9

• Support for Sparse MoE models like Camelidae and Sparsetral

  enhancementgood first issue
  ggml-org/llama.cpp#5365 · Filter by author candre23 opened on Feb 6, 2024
  6

• MiniCPM 2b model support?

  enhancementgood first issue
  ggml-org/llama.cpp#5276 · Filter by author KnutJaegersberg opened on Feb 2, 2024
  26

• llama : integer type consistency in llama.h

  enhancementgood first issuerefactoringroadmap
  ggml-org/llama.cpp#4574 · Filter by author MarcusDunn opened on Dec 21, 2023
  4

• GGUF endianness cannot be determined from GGUF itself

  breaking changeenhancementgood first issue
  ggml-org/llama.cpp#3957 · Filter by author philpax opened on Nov 5, 2023
  20