dela
584f7e9e73
Standalone tree split from LLMRL/projects/kda. Includes Triton dt_bias backward fix, train_k3 --preset 0.5b, SFT, Docker runtime, and tests.
12 lines
385 B
Python
12 lines
385 B
Python
"""Context-parallel hooks referenced by KDA fwd/bwd. Not implemented here."""
|
|
|
|
|
|
def _cp_unsupported(*args, **kwargs):
|
|
raise RuntimeError("Context parallel is not included in the vendored KDA kernels")
|
|
|
|
|
|
chunk_gated_delta_rule_fwd_h_pre_process = _cp_unsupported
|
|
compress_h0 = _cp_unsupported
|
|
chunk_gated_delta_rule_bwd_dhu_pre_process = _cp_unsupported
|
|
expand_h0 = _cp_unsupported
|