[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
@@ -26,8 +26,8 @@ from vllm.v1.core.kv_cache_utils import (
)
from vllm.v1.core.sched.scheduler import Scheduler
from vllm.v1.kv_cache_interface import (
CircularBufferSpec,
FullAttentionSpec,
KpoolTailSpec,
KVCacheConfig,
KVCacheGroupSpec,
MambaSpec,
@@ -2308,12 +2308,11 @@ def test_opted_out_scratch_group_keeps_partial_hash_hits():
),
KVCacheGroupSpec(
["tail"],
KpoolTailSpec(
CircularBufferSpec(
block_size=mamba_block_size,
num_kv_heads=1,
head_size=1,
dtype=torch.float32,
sliding_window=mamba_block_size,
),
),
],
@@ -2366,12 +2365,11 @@ def test_kpool_tail_supports_128_token_partial_hash_hits():
),
KVCacheGroupSpec(
["tail"],
KpoolTailSpec(
CircularBufferSpec(
block_size=kpool_block_size,
num_kv_heads=1,
head_size=1,
dtype=torch.float32,
sliding_window=kpool_block_size,
),
),
],