[kv_offload+HMA][13/N]: Enable HMA support (#41445)

This is the final PR in a series to enables HMA support for the
offloading connector. The connector advertises `SupportsHMA`
and is validated with unit tests and e2e tests.

Signed-off-by: Or Ozeri <oro@il.ibm.com>
This commit is contained in:
Or Ozeri
2026-05-01 12:30:03 +01:00
committed by GitHub
parent 7075df79b3
commit 2fa1f8ec00
6 changed files with 661 additions and 250 deletions
+2
View File
@@ -103,6 +103,7 @@ def create_vllm_config(
kv_load_failure_policy: Literal["recompute", "fail"] = "fail",
kv_connector: str = "NixlConnector",
kv_role: str = "kv_both",
disable_hybrid_kv_cache_manager: bool | None = None,
) -> VllmConfig:
"""Initialize VllmConfig For Testing."""
model_config = ModelConfig(
@@ -118,6 +119,7 @@ def create_vllm_config(
max_model_len=max_model_len,
enable_chunked_prefill=enable_chunked_prefill,
is_encoder_decoder=model_config.is_encoder_decoder,
disable_hybrid_kv_cache_manager=disable_hybrid_kv_cache_manager,
)
# Cache config, optionally force APC
cache_config = CacheConfig(