[Core] Add MRV2 virtual-batch PCP for MLA (#46570)

Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
Co-authored-by: Codex <noreply@openai.com>
Co-authored-by: OpenAI Codex <codex@openai.com>
Co-authored-by: Matthew Bonanni <mbonanni@redhat.com>
This commit is contained in:
Lucas Wilkinson
2026-07-19 02:53:15 +00:00
committed by GitHub
co-authored by Codex OpenAI Codex Matthew Bonanni
parent 9243e0124e
commit b6ff8a2f50
39 changed files with 1204 additions and 196 deletions
@@ -36,13 +36,12 @@ def build_offloading_config(
engine_id = kv_transfer_config.engine_id
parallel_config = vllm_config.parallel_config
context_parallel_factor = (
parallel_config.decode_context_parallel_size
* parallel_config.prefill_context_parallel_size
)
groups = tuple(
OffloadingGroupConfig(
tokens_per_block=(group.kv_cache_spec.block_size * context_parallel_factor),
tokens_per_block=(
group.kv_cache_spec.block_size
* parallel_config.decode_context_parallel_size
),
layer_names=tuple(group.layer_names),
)
for group in kv_cache_config.kv_cache_groups