kherud/java-llama.cpp

Issues

• Segfault on model open and close

  #80 opened 2 months ago by shuttie
  2

• Android inference issue "A FORTIFY: pthread_mutex_lock called on a destroyed mutex"

  #79 opened 2 months ago by xunuohope1107
  0

• Process finished with exit code -1073741819 (0xC0000005) while trying to infer CodeGemma-2B GGUF

  #77 opened 2 months ago by 32kda
  7

• Add suuport to params.lora_adapters in newer llama.cpp (after b3534)

  #78 opened 2 months ago by xunuohope1107
  3

• 3.4.0 packaging regression: CUDA libs packed with the main JAR

  #76 opened 3 months ago by shuttie
  2

• JNI

  #72 opened 4 months ago by ys2940
  3

• Add vocab_only

  #70 opened 5 months ago by ardinursyamsu
  1

• What's the model path in android?

  #69 opened 5 months ago by Raffa064
  5

• fail with snowflake-arctic-embed-l

  #59 opened 5 months ago by fbellomi
  6

• Android build error : libllama.so is incompatible with aarch64linux

  #50 opened 9 months ago by RageshAntonyHM
  1

• Can't pass the test

  #68 opened 6 months ago by ardinursyamsu
  2

• Issues with logging in v3

  #66 opened 6 months ago by martinhybergTE
  8

• Interrupting inference?

  #62 opened 6 months ago by jrtp
  7

• 'ggml-common.h' file not found On MacOS

  #61 opened 6 months ago by MarchLiu
  2

• Java tests failed when CUDA enabled on version 3.0.0

  #54 opened 7 months ago by RFYoung
  5

• 'ggml-metal.metal' not found

  #16 opened a year ago by Solido
  7

• llama_init_from_gpt_params: error: failed to apply lora adapter

  #15 opened 8 months ago by mordesku
  4

• Prebuilt x86 linux libs use EVEX encoding for AVX instructions, causing SIGILL

  #25 opened 8 months ago by AutonomicPerfectionist
  3

• Questions and Feedback

  #18 opened 8 months ago by Solido
  3

• Missing libjllama on Linux aarch64

  #17 opened 8 months ago by AutonomicPerfectionist
  3

• version `GLIBCXX_3.4.29' not found

  #19 opened 8 months ago by sc3sc3
  3

• multiple definition of `pthread_mutex_destroy'; first defined here

  #20 opened 8 months ago by fucksmile
  1

• empty response

  #23 opened 8 months ago by mbofb
  3

• Need help: No native library found for os.name=Windows, os.arch=x86_64

  #24 opened 8 months ago by j0schihatake
  1

• WSL/Java 17 is supported?

  #26 opened 8 months ago by javierfd
  8

• Core dump on Ubuntu

  #27 opened 8 months ago by DWAA1660
  5

• Latest version did not publish to Maven

  #28 opened 8 months ago by AutonomicPerfectionist
  0

• model.generate aborts with "libc++abi: terminating due to uncaught exception of type std::length_error: basic_string"

  #29 opened 8 months ago by abadelt
  1

• java.lang.NoSuchFieldError: de.kherud.llama.InferenceParameters.antiPrompt [Ljava/lang/String;

  #31 opened 8 months ago by enimatek-nl
  2

• SIGILL (0x4) at pc=0x00007fe92acb5142, pid=3952, tid=4017

  #30 opened 8 months ago by siddhsql
  1

• Handling multi token utf8 bytes in streaming mode

  #47 opened 8 months ago by hvisser
  3

• java 8 patch

  #36 opened 8 months ago by litongjava
  1

• How build project on windows?

  #40 opened 8 months ago by Maxon081102
  4

• Suggestion: make obtaining the language model from the web more convenient

  #48 opened 8 months ago by mbofb
  1

• SIGSEGV Error During Execution of Embedding Code

  #49 opened 8 months ago by hide212131
  3

• "Failed to load native library" when using custom llama.cpp with GPU acceleration build

  #53 opened 8 months ago by PauloIVM
  3

• Update to a newer version of llama.cpp

  #51 opened 8 months ago by RFYoung
  2

• where is default llama and jllama dlls?

  #44 opened 10 months ago by siddhsql
  2

• Completion seems to ignore EOS token

  #45 opened 10 months ago by hvisser
  3

• not getting gpu acceleration on windows

  #43 opened 10 months ago by siddhsql
  3

• Android support?

  #37 opened 10 months ago by samolego
  19

• Deleting local references where it doesn't exist

  #38 opened 10 months ago by samolego
  0

• Support multimodal inputs

  #34 opened a year ago by yeroc
  1

• How to use GPU to run the modes, like to set "-ngl N, -- n-Gpu-layers N" in the llama.cpp project?

  #32 opened a year ago by vo1d07
  2

• java.lang.UnsatisfiedLinkError: 'void de.kherud.llama.LlamaModel.delete()' on LlamaModel.close

  #21 opened a year ago by mikhalchenko-alexander
  1

• adapting MainExample.java for Builder pattern

  #22 opened a year ago by mbofb
  0

• "could not load model from given file path" issue caused by jllama.dll

  #13 opened a year ago by mymagicpower
  2

• Failed to load native library: xxxx-jllama.dll. (missing)

  #11 opened a year ago by mymagicpower
  9

• GPU build issue: failed to load model

  #12 opened a year ago by mymagicpower
  2

• Could not find jni.h

  #10 opened a year ago by mymagicpower
  3