auto-round
fix lots of gguf critic bugs and support imatrix in rtn mode
#595
Merged

Commits
  • try to setup imatrix baseline
    wenhuach21 committed 1 year ago
  • add todo
    wenhuach21 committed 1 year ago
  • [pre-commit.ci] auto fixes from pre-commit.com hooks
    pre-commit-ci[bot] committed 1 year ago
  • update
    wenhuach21 committed 1 year ago
  • Merge branch 'main' into imatrix
    wenhuach21 committed 1 year ago
  • Merge branch 'imatrix' of https://github.com/intel/auto-round into imatrix
    wenhuach21 committed 1 year ago
  • tmp change
    wenhuach21 committed 1 year ago
  • update
    wenhuach21 committed 1 year ago
  • [pre-commit.ci] auto fixes from pre-commit.com hooks
    pre-commit-ci[bot] committed 1 year ago
  • tiny change
    wenhuach21 committed 1 year ago
  • clear memory
    wenhuach21 committed 1 year ago
  • avg the act
    wenhuach21 committed 1 year ago
  • quantize embedding and lm_head in rtn mode
    wenhuach21 committed 1 year ago
  • fix bugs
    wenhuach21 committed 1 year ago
  • support 3bits and 6 bits imatrix
    wenhuach21 committed 1 year ago
  • fix multi gpu issue
    wenhuach21 committed 1 year ago
  • Tried to fix the MoE issue, but it hasn't been addressed yet.
    wenhuach21 committed 1 year ago
  • fix
    wenhuach21 committed 1 year ago
  • tmp change
    wenhuach21 committed 1 year ago
  • tmp change
    wenhuach21 committed 1 year ago
  • fix moe issue
    wenhuach21 committed 1 year ago
  • fix q2_k_s tiny
    wenhuach21 committed 1 year ago
  • fix and support embedding quantization in tuning
    wenhuach21 committed 1 year ago
  • support lm-head tuning for gguf by default
    wenhuach21 committed 1 year ago
  • [pre-commit.ci] auto fixes from pre-commit.com hooks
    pre-commit-ci[bot] committed 1 year ago
  • fix permute issue
    wenhuach21 committed 1 year ago
  • unify packing code for different devices
    wenhuach21 committed 1 year ago
  • fix issues
    wenhuach21 committed 1 year ago
  • fix issues
    wenhuach21 committed 1 year ago
  • fix issues
    wenhuach21 committed 1 year ago
  • fix
    wenhuach21 committed 1 year ago
  • fix
    wenhuach21 committed 1 year ago
  • fix
    wenhuach21 committed 1 year ago
  • fix
    wenhuach21 committed 1 year ago
  • fix one ut
    wenhuach21 committed 1 year ago
  • support fallback and fix ut
    wenhuach21 committed 1 year ago
  • fix ut and add disable_opt_rtn
    wenhuach21 committed 1 year ago
  • change one file name
    wenhuach21 committed 1 year ago
  • porting mixed bits setting from gguf
    wenhuach21 committed 1 year ago
  • fix
    wenhuach21 committed 1 year ago
  • fix
    wenhuach21 committed 1 year ago
  • fix
    wenhuach21 committed 1 year ago
  • fix
    wenhuach21 committed 1 year ago
  • fix
    wenhuach21 committed 1 year ago
Loading