[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
@@ -553,12 +553,10 @@ def test_compute_slot_mapping_uses_named_launcher_inputs(monkeypatch) -> None:
owner = ComputeSlotMappingKernel()
compile_key = owner.CompileKey(
kv_cache_block_size=16,
blocks_per_kv_block=1,
total_cp_world_size=2,
total_cp_rank=1,
cp_kv_cache_interleave_size=1,
block_table_stride=128,
block_size=16,
)
launches: list[tuple[Any, ...]] = []
@@ -574,7 +572,6 @@ def test_compute_slot_mapping_uses_named_launcher_inputs(monkeypatch) -> None:
assert inputs["block_table_stride"] == 128
assert kwargs == {
"KV_CACHE_BLOCK_SIZE": 16,
"BLOCKS_PER_KV_BLOCK": 1,
"TOTAL_CP_WORLD_SIZE": 2,
"TOTAL_CP_RANK": 1,
"CP_KV_CACHE_INTERLEAVE_SIZE": 1,