IBM/text-generation-inference

Issues

• Problem loading granite-3b in small MIG partitions

  #104 opened 3 months ago by ccamacho
  0

• Official container image

  #102 opened 3 months ago by josephrocca
  2

• Is there a way to see all the supported parameters for TGIS?

  #95 opened 4 months ago by bdattoma
  0

• Generation does not terminate with EOS token for the vinai/PhoGPT-4B-Chat model

  #91 opened 4 months ago by tjohnson31415
  0

• deepseek-coder-33b-instruct model on tgis fails with flash attention and generates wrong output without flash attention

  #92 opened 4 months ago by maxdebayser
  2

• GitHub action failing with "No space left on device" error

  #11 opened 7 months ago by ckadner
  0

• Doc Request: PREFIX_STORE_PATH in README

  #19 opened 9 months ago by gabe-l-hart
  0

• Optimizing Latency in FlashLlamaLayer.mlp During First Token Generation

  #13 opened a year ago by truenorth8
  0

• TGIS build requires PyTorch nightly

  #6 opened a year ago by Xaenalt
  7

• Unable to launch the execution engine (server)

  #5 opened a year ago by antferdom
  4

• DTYPE_STR is not set, does not appear to be inferred automatically

  #7 opened a year ago by Xaenalt
  2

• TGIS fails to load model when not in a directory

  #8 opened a year ago by Xaenalt
  2

• [P0] Create TGIS community images/CI for Open Data Hub

  #3 opened a year ago by heyselbi
  1

• [P0] Review/validate existing dockerfile for Open Data Hub

  #2 opened a year ago by heyselbi
  1

• [P2] Configure configure job publish pypi for Open Data Hub

  #1 opened a year ago by heyselbi
  1