[KV Cache] GLM-5.3-Flash: use the generic packed KV layout; CircularBufferSpec tail with speculative ring slots (#57169)

Signed-off-by: Yifan Qiao <yifanqiao@inferact.ai>
Signed-off-by: Dakai An <dakaian108@gmail.com>
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
Co-authored-by: Yifan Qiao <yifanqiao@inferact.ai>
Co-authored-by: OpenAI Codex <noreply@openai.com>
Co-authored-by: OpenAI Codex <codex@openai.com>
Co-authored-by: Lucas Wilkinson <lwilkins@redhat.com>
Co-authored-by: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Co-authored-by: Lucas Wilkinson <LucasWilkinson@users.noreply.github.com>
This commit is contained in:
Dakai An
2026-10-09 15:48:37 -04:00
committed by GitHub
co-authored by Yifan Qiao OpenAI Codex OpenAI Codex Lucas Wilkinson Claude Opus 5.5 Lucas Wilkinson
parent 3766a67a32
commit 02e55d2af3
83 changed files with 1280 additions and 1986 deletions
+6
View File
@@ -963,6 +963,9 @@ def test_propose(method, attn_backend, num_speculative_tokens, monkeypatch):
# Mock draft_attn_groups for attention metadata building.
mock_attn_group = mock.MagicMock()
mock_attn_group.get_metadata_builder.return_value = attn_metadata_builder
mock_attn_group.build_metadata_for_drafting = (
attn_metadata_builder.build_for_drafting
)
mock_attn_group.layer_names = list(proposer._draft_attn_layer_names)
mock_attn_group.kv_cache_spec = attn_metadata_builder.kv_cache_spec
proposer.draft_attn_groups = [mock_attn_group]
@@ -1066,6 +1069,9 @@ def test_propose_stores_probabilistic_draft_probs(attn_backend, monkeypatch):
)
mock_attn_group = mock.MagicMock()
mock_attn_group.get_metadata_builder.return_value = attn_metadata_builder
mock_attn_group.build_metadata_for_drafting = (
attn_metadata_builder.build_for_drafting
)
mock_attn_group.layer_names = list(proposer._draft_attn_layer_names)
mock_attn_group.kv_cache_spec = attn_metadata_builder.kv_cache_spec
proposer.draft_attn_groups = [mock_attn_group]