-
Remove bundled execution code
-
docs: minimize repository card
-
Add code/quantize/ternary_pack.py
-
Add code/quantize/ternary_kernel.py
-
Add code/quantize/quantizer.py
-
Add code/quantize/moe_round_worker.py
-
Add code/quantize/k_preprocessor_ternary.py
-
Add code/quantize/e2m_atq_fwrd_multigpu.py
-
Add code/quantize/e2m_atq_fwrd.py
-
Add code/quantize/const.py
-
Add code/quantize/E2M_ATQ_mixed_precision.py
-
Add code/quantize/E2M_ATQ_groupwise.py
-
Add code/quantize/E2M_ATQ_9level.py
-
Add code/quantize/E2M_ATQ_8level.py
-
Add code/quantize/E2M_ATQ_7level.py
-
Add code/quantize/E2M_ATQ_6level.py
-
Add code/quantize/E2M_ATQ_4level.py
-
Add code/quantize/E2M_ATQ_11level.py
-
Add code/quantize/E2M_ATQ_10level.py
-
Add code/run_benchmark_qwen36_multilevel.py
-
Add code/taylor_fisher_proxy.py
-
Add code/branch_bound_search.py
-
Add code/optimize_twla_hierarchical_nll.py
-
Add code/build_twla_expert_level_bank.py
-
Add model card
-
Add files using upload-large-folder tool
-
Add model card, training code, and inference code
-
initial commit