[3/N] HiSparse: host-resident sparse-MLA decode hot-buffering (#53781)

Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
Signed-off-by: Lucas Wilkinson <lwilkinson@neuralmagic.com>
Signed-off-by: Matthew Bonanni <matthew@neuralmagic.com>
Signed-off-by: Nicolò Lucchesi <nicolo.lucchesi@mistral.ai>
Co-authored-by: OpenAI Codex <codex@openai.com>
Co-authored-by: Lucas Wilkinson <lwilkins@redhat.com>
Co-authored-by: Lucas Wilkinson <lwilkinson@neuralmagic.com>
Co-authored-by: Nicolò Lucchesi <nicolo.lucchesi@mistral.ai>
Co-authored-by: OpenAI Codex <noreply@openai.com>
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
Co-authored-by: Lucas Wilkinson <LucasWilkinson@users.noreply.github.com>
This commit is contained in:
Matthew Bonanni
2026-09-12 00:36:47 -04:00
committed by GitHub
co-authored by OpenAI Codex Lucas Wilkinson Lucas Wilkinson Nicolò Lucchesi OpenAI Codex Claude Opus 5 Lucas Wilkinson
parent 120ec4ebd2
commit d43bb2f37f
124 changed files with 14262 additions and 906 deletions
@@ -78,13 +78,11 @@ def ensure_kv_transfer_initialized(
global _KV_CONNECTOR_AGENT
if vllm_config.kv_transfer_config is None:
if _KV_CONNECTOR_AGENT is not None:
return
if (
vllm_config.kv_transfer_config.is_kv_transfer_instance
and _KV_CONNECTOR_AGENT is None
):
kv_transfer_config = vllm_config.kv_transfer_config
if kv_transfer_config is not None and kv_transfer_config.is_kv_transfer_instance:
# NIXL P/D requires an interleave_size equal to block_size.
vllm_config.adjust_dcp_kv_cache_interleave_size(kv_cache_config)
_sync_engine_id_across_tp(vllm_config)