Atome-FE/llama-node

Issues

• What files are compatible?

  #124 opened 3 months ago by bedcoding
  0

• Alternative?

  #123 opened 6 months ago by linonetwo
  1

• napi: not found on debian bullseye

  #118 opened 10 months ago by loretoparisi
  5

• fatal runtime error: Rust cannot catch foreign exceptions

  #109 opened a year ago by HolmesDomain
  5

• GGUF support?

  #122 opened 7 months ago by nildotdev
  0

• cannot use RWKV models

  #121 opened 8 months ago by rozek
  16

• Instructions for use with Electron

  #120 opened 9 months ago by bishwenduk029
  0

• Can't run example on llama-2-13b-chat q4_0

  #116 opened 10 months ago by gioragutt
  2

• GPU version build not using GPU

  #114 opened a year ago by dspasyuk
  11

• use with Next.js (webpack fails to load binary file)

  #93 opened a year ago by eagor
  3

• Time printings are gone

  #119 opened 10 months ago by CodeJjang
  0

• The requested module 'llama-node/dist/llm/llama-cpp.js' does not provide an export named 'LoadConfig'

  #117 opened 10 months ago by heaversm
  0

• Support for passing grammars

  #115 opened 10 months ago by arthurwolf
  0

• Discord Access

  #107 opened 10 months ago by HolmesDomain
  1

• Segmentation fault

  #113 opened a year ago by ZGltYQ
  1

• [Error: Failed to get embeddings] { code: 'GenericFailure' }

  #110 opened a year ago by ThomasDev28
  0

• Code only using 4 CPU, when I have 16 CPU

  #69 opened a year ago by gaurav-cointab
  3

• foreign exception error

  #76 opened a year ago by ralyodio
  12

• Llama2 quantized q5_1

  #108 opened a year ago by HolmesDomain
  1

• Unable to load latest GGML models using llama.cpp after latest quantisation changes

  #60 opened a year ago by dev-bre
  3

• 中文乱码

  #104 opened a year ago by linonetwo
  0

• Use custom tokenizer

  #105 opened a year ago by linonetwo
  0

• Should bring details in error message

  #102 opened a year ago by linonetwo
  0

• Unsupported file version 101 when loading rwkv

  #101 opened a year ago by linonetwo
  0

• Issue to build GPU version

  #99 opened a year ago by dspasyuk
  1

• Llama.cpp Typescript: Cannot find name 'LoadModel'

  #91 opened a year ago by synw
  0

• Support for the new k-quant methods in Llama.cpp

  #95 opened a year ago by synw
  0

• the software has no reaction with no errors

  #94 opened a year ago by adambnn
  0

• Can't run the example on MacOS M1 pro

  #92 opened a year ago by greenido
  0

• Bumping from 0.1.5 to 0.1.6 resulting with `Error: invariant broken`

  #90 opened a year ago by NitayRabi
  0

• no kernel image is available for execution on the device

  #83 opened a year ago by determo13
  2

• llama-node/llama-cpp uses more memory than standalone llama.cpp with the same parameters

  #85 opened a year ago by fardjad
  3

• Ggml v3 support in Llama.cpp

  #84 opened a year ago by synw
  4

• Error: Missing field `nGpuLayers`

  #80 opened a year ago by bakiwebdev
  6

• Failed to convert napi value into rust type `bool`

  #79 opened a year ago by determo13
  1

• Error: Too many tokens predicted

  #81 opened a year ago by dhd5076
  1

• Segmentation fault local cuda build

  #78 opened a year ago by chrgeor
  0

• [ERROR] cublas `TypeError: this.instance.inference is not a function`

  #73 opened a year ago by tchereau
  3

• Embeddings.js file does not work correctly

  #77 opened a year ago by skirodev
  0

• langchain integration

  #56 opened a year ago by luca-saggese
  2

• basic unified API for all backends

  #55 opened a year ago by end-me-please
  3

• app crashes when input is too long

  #74 opened a year ago by ralyodio
  6

• getting error after second run

  #71 opened a year ago by ralyodio
  0

• TypeError: llm._modelType is not a function

  #70 opened a year ago by gaurav-cointab
  1

• Illegal instruction (core dumped)

  #72 opened a year ago by itz-coffee
  4

• req: support async/await

  #68 opened a year ago by ralyodio
  8

• Error: Failed to convert napi value Function into rust type `f64`

  #67 opened a year ago by ralyodio
  5

• is this supposed to have a gpu to run?

  #64 opened a year ago by ralyodio
  2

• [Error: Could not load model] { code: 'GenericFailure' }

  #57 opened a year ago by ralyodio
  8

• ¿Update cross-compile.mts with aarch64 architecture?

  #54 opened a year ago by yupihello
  1