[CI] Ignore ruff D209, rejoin the docstrings it split, and silence incompatible-rule warnings (#57212)
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com> Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
This commit is contained in:
co-authored by
Claude Opus 5
parent
1085b64425
commit
651a88c09a
@@ -396,8 +396,7 @@ class ExtractHiddenStatesProposer:
|
||||
|
||||
def validate_same_kv_cache_group(self, kv_cache_config: KVCacheConfig) -> None:
|
||||
"""Validate all drafting layers belong to the same KV cache group
|
||||
and record the group index for common_attn_metadata selection.
|
||||
"""
|
||||
and record the group index for common_attn_metadata selection."""
|
||||
assert len(self.attn_layer_names) == 1
|
||||
layer = self.attn_layer_names[0]
|
||||
for gid, group in enumerate(kv_cache_config.kv_cache_groups):
|
||||
|
||||
@@ -221,8 +221,7 @@ class Gemma4Proposer(SpecDecodeBaseProposer):
|
||||
def validate_same_kv_cache_group(self, kv_cache_config: KVCacheConfig) -> None:
|
||||
"""Draft layers span multiple KV cache groups (sliding + full
|
||||
attention with different head dimensions), so skip the base
|
||||
class single-group assertion.
|
||||
"""
|
||||
class single-group assertion."""
|
||||
|
||||
def initialize_attn_backend(
|
||||
self,
|
||||
@@ -230,8 +229,7 @@ class Gemma4Proposer(SpecDecodeBaseProposer):
|
||||
kernel_block_sizes: list[int] | None = None,
|
||||
) -> None:
|
||||
"""Create separate AttentionGroup objects per KV cache spec
|
||||
so that each head-dim variant gets its own metadata builder.
|
||||
"""
|
||||
so that each head-dim variant gets its own metadata builder."""
|
||||
all_attn_layers = get_layers_from_vllm_config(
|
||||
self.vllm_config,
|
||||
AttentionLayerBase, # type: ignore[type-abstract]
|
||||
|
||||
@@ -785,8 +785,7 @@ class SpecDecodeBaseProposer:
|
||||
block_size: int,
|
||||
) -> torch.Tensor:
|
||||
"""Update positions, slot mappings, and sequence metadata for the
|
||||
next draft step. Returns the updated positions tensor.
|
||||
"""
|
||||
next draft step. Returns the updated positions tensor."""
|
||||
positions_1d = positions[0] if self.uses_mrope else positions
|
||||
if self.uses_mrope:
|
||||
out_pos = self.mrope_positions[0, :batch_size]
|
||||
|
||||
@@ -847,6 +847,5 @@ def update_num_computed_tokens_for_batch_change(
|
||||
|
||||
def unconditional_to_conditional_rates(rates: list[float]) -> list[float]:
|
||||
"""Convert per-position unconditional rates to per-position conditional
|
||||
rates for the early-terminating rejection loop (c_i = p_i / p_{i-1}).
|
||||
"""
|
||||
rates for the early-terminating rejection loop (c_i = p_i / p_{i-1})."""
|
||||
return [p / q if q > 0.0 else 0.0 for p, q in zip(rates, [1.0, *rates[:-1]])]
|
||||
|
||||
Reference in New Issue
Block a user