v0.30.0rc2 fixes NIXL receive reports for notification-only requests
The v0.30.0rc2 release includes a bugfix for NIXL to avoid generating receive reports for notification-only requests.
vLLM v0.29.0 applies dense prefix cache default to hybrid models
The vLLM project released version 0.29.0, which includes a core bugfix regarding the dense prefix cache.
v0.29.0rc5 changes default prefix_cache_retention_interval to dense for Mamba
The v0.29.0rc5 release updates the default value of the `prefix_cache_retention_interval` parameter to `dense` specifically for Mamba models.
v0.29.0rc2 fixes SHM worker cache for prefix-covered items
The v0.29.0rc2 release includes a bugfix for the SHM worker cache to properly handle prefix-covered items.