[Mamba] Share RecoverSSM commit kernels and helpers across models
RecoverSSM's commit-plan and conv-window compaction kernels are model independent. Move them from models/kimi_k3 into model_executor/layers/mamba/ops/recoverssm.py (Kimi-K3 keeps its private names as import aliases; kernel source unchanged), add mamba/recoverssm_utils.py (activation predicate, argument validation) and the generic spec-row/request mapping helpers to v1/attention/backends/recoverssm_metadata.py. CacheConfig.use_kda_recoverssm becomes use_recoverssm: the switch now selects RecoverSSM for any model whose recurrent layers implement it, not only KDA. No functional change for Kimi-K3. Signed-off-by: Jürgen Schmied <juergenschmied70@gmail.com> Co-authored-by: Claude <noreply@anthropic.com>
This commit is contained in:
@@ -259,7 +259,7 @@ def _create_decode_vllm_config(
|
||||
num_speculative_tokens: int = 0,
|
||||
dynamic_spec_schedule: list[tuple[int, int, int]] | None = None,
|
||||
max_num_seqs: int = 8,
|
||||
use_kda_recoverssm: bool = False,
|
||||
use_recoverssm: bool = False,
|
||||
) -> MagicMock:
|
||||
compilation_config = CompilationConfig(
|
||||
cudagraph_mode="FULL_AND_PIECEWISE",
|
||||
@@ -274,7 +274,7 @@ def _create_decode_vllm_config(
|
||||
max_num_seqs=max_num_seqs
|
||||
)
|
||||
vllm_config.parallel_config = ParallelConfig()
|
||||
vllm_config.cache_config = SimpleNamespace(use_kda_recoverssm=use_kda_recoverssm)
|
||||
vllm_config.cache_config = SimpleNamespace(use_recoverssm=use_recoverssm)
|
||||
vllm_config.num_speculative_tokens = num_speculative_tokens
|
||||
if dynamic_spec_schedule is None:
|
||||
vllm_config.speculative_config = None
|
||||
@@ -293,7 +293,7 @@ def _make_spec_decode_manager(
|
||||
num_speculative_tokens: int = 0,
|
||||
dynamic_spec_schedule: list[tuple[int, int, int]] | None = None,
|
||||
max_num_seqs: int = 8,
|
||||
use_kda_recoverssm: bool = False,
|
||||
use_recoverssm: bool = False,
|
||||
varlen_decode: bool = False,
|
||||
) -> gpu_cudagraph_utils.CudaGraphManager:
|
||||
monkeypatch.setattr(
|
||||
@@ -312,7 +312,7 @@ def _make_spec_decode_manager(
|
||||
num_speculative_tokens=num_speculative_tokens,
|
||||
dynamic_spec_schedule=dynamic_spec_schedule,
|
||||
max_num_seqs=max_num_seqs,
|
||||
use_kda_recoverssm=use_kda_recoverssm,
|
||||
use_recoverssm=use_recoverssm,
|
||||
),
|
||||
device=torch.device("cpu"),
|
||||
cudagraph_mode=CUDAGraphMode.FULL_AND_PIECEWISE,
|
||||
|
||||
Reference in New Issue
Block a user