[Rebase] Rebase to vLLM 0.30.0 (#7820)

Signed-off-by: tzhouam <tzhouam@connect.ust.hk>
Signed-off-by: Gao Han <hgaoaf@connect.ust.hk>
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
Co-authored-by: Gao Han <hgaoaf@connect.ust.hk>
This commit is contained in:
authored and GitHub committed 2026-09-22 15:52:01 +00:00
1 parent ca14e635f5
commit 59db6a4285
59 files changed
+1032 -300

No files matched your search

@@ -260,7 +260,6 @@ class DiffusionKVModelRunnerBackend:
cp_rank = get_dcp_group().rank_in_group if cp_size > 1 else 0
cp_interleave = parallel_config.cp_kv_cache_interleave_size
kv_caches: list[torch.Tensor | list[torch.Tensor]] = []
previous_adapter_caches = {
layer_name: adapter.kv_cache for layer_name, adapter in self._kv_cache_layer_adapters.items()
}
@@ -292,19 +291,20 @@ class DiffusionKVModelRunnerBackend:
layers=self._kv_cache_layer_adapters,
resolve_row=self._resolve_paged_attention_row,
)
# vLLM 0.29 reads the resolved physical layout when allocating,
# and dropped attn_groups/cache_dtype from the signature.
# f2aad6aa70 (#56888): first arg is forward_context; caches
# are returned as a dict instead of appended to a runner list.
adopt_kv_cache_layout(self.vllm_config, kv_cache_config)
for layer_adapter in self._kv_cache_layer_adapters.values():
assert_backend_layout_supported(self.vllm_config, getattr(layer_adapter, "attn_backend", None))
init_kv_cache(
kv_caches,
kv_caches_dict = init_kv_cache(
self.vllm_config.compilation_config.static_forward_context,
kv_cache_config,
self.device,
kernel_block_sizes,
self.vllm_config,
block_tables=block_tables,
)
kv_caches = list(kv_caches_dict.values())
except Exception:
for layer_name, previous_cache in previous_adapter_caches.items():
self._kv_cache_layer_adapters[layer_name].kv_cache = previous_cache