[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
+2 -4
View File
@@ -95,11 +95,9 @@ def prepare_dcp_dummy_context_metadata(
max_valid_block_id = kv_cache_config.num_blocks - 1
assert max_valid_block_id > 0
for blk_table in input_batch.block_table.block_tables:
max_row_blocks = (
blk_table.max_num_blocks_per_req // blk_table.blocks_per_kv_block
)
block_ids = [
(block_idx % max_valid_block_id) + 1 for block_idx in range(max_row_blocks)
(block_idx % max_valid_block_id) + 1
for block_idx in range(blk_table.max_num_blocks_per_req)
]
for req_idx in range(num_reqs):
blk_table.add_row(block_ids, req_idx)