Commit History

Author SHA1 Message Date
  AlpinDale 50c2434267 move megatron to a top-level directory 9 months ago
  AlpinDale 4d33ce60da feat: Triton flash attention backend for ROCm (#407) 9 months ago
  AlpinDale 41beab5dc1 add exllamav2 tensor paralell, fused MoE for GPTQ/AWQ 9 months ago
  AlpinDale 0f1399c135 feat: attention refactor part 2 9 months ago
  AlpinDale d1786645a3 fix formatting 9 months ago
  AlpinDale 688d56993a add logit scale for command-r 9 months ago
  AlpinDale f1ea36a445 add some imports 9 months ago
  AlpinDale f8dfac6372 chore: attention refactor and upstream sync apr01 (#365) 9 months ago
  AlpinDale da223153c6 feat&fix: cohere support and missing GPU blocks (#333) 10 months ago
  AlpinDale e42a78381a feat: switch from pylint to ruff (#322) 10 months ago
  AlpinDale e31c6f0b45 feat: refactor modeling logic and support more models (#274) 11 months ago
  AlpinDale 842912d022 feat: on-the-fly gguf conversion (#250) 11 months ago
  AlpinDale c3a221eb02 feat: GGUF, QuIP#, and Marlin support (#228) 1 year ago
  AlpinDale 8fa608aeb7 feat: replace Ray with NCCL for control plane comms (#221) 1 year ago
  AlpinDale b9b295d74e chore: backlogs 1 (#191) 1 year ago
  AlpinDale 7d91e9e0f2 feat: CUDA graphs (#172) 1 year ago
  AlpinDale 653da510d1 chore: rewrite InputMetadata (#143) 1 year ago
  AlpinDale 8b2bbbd98b chore: attention rewrite + models (#135) 1 year ago
  AlpinDale 0d51eac374 feat: awq for all models (#124) 1 year ago
  AlpinDale e7b6a2d5a0 chore: tensor parallel refactors part 2 (#116) 1 year ago
  AlpinDale 74604eb252 fix: pylint complaints (#91) 1 year ago
  AlpinDale efc6f7fbec chore: reformats (#90) 1 year ago
  AlpinDale a6a4220fa6 feat: refactor megatron and quants (#57) 1 year ago
  AlpinDale 0495c50a3e GPTQ+exllama support (#21) 1 year ago
  AlpinDale 75c27d3e65 massive overhaul 1 year ago
  AlpinDale 6b9561ef07 adapt TGI incremental detokenization 1 year ago
  AlpinDale 45f6d9f923 initial refactor commit 1 year ago
  AlpinDale 06e71fc492 feat: add GPT-NeoX support for testing purposes 1 year ago