[GLM 5.3 Perf] Enable fused multi-step decode, 13.3% E2E throughput improvement for concurrency 1 (#57443)
Signed-off-by: yewentao256 <zhyanwentao@126.com>
This commit is contained in:
@@ -373,6 +373,7 @@ class DraftModelSpeculator(BaseSpeculator):
|
||||
kv_cache_config=self.kv_cache_config,
|
||||
causal=causal,
|
||||
seq_lens_cpu_upper_bound=draft_seq_lens_cpu_upper_bound,
|
||||
positions=self.input_buffers.positions[:num_tokens],
|
||||
is_prefilling=self.draft_is_prefilling[:num_reqs_padded],
|
||||
)
|
||||
return attn_metadata
|
||||
|
||||
Reference in New Issue
Block a user