[Rebase] Rebase to vLLM 0.29.0 (#7230)

Signed-off-by: tzhouam <tzhouam@connect.ust.hk>
Signed-off-by: Zhou Taichang <tzhouam@connect.ust.hk>
Co-authored-by: Claude Opus 5 <noreply@anthropic.com>
This commit is contained in:
Zhou TaichangandClaude Opus 5 authored and GitHub committed 2026-09-10 12:08:28 +08:00
1 parent 333f14e97e
commit aff7d64948
120 files changed
+2958 -1690

No files matched your search

@@ -279,17 +279,17 @@ def _install_native_modules(monkeypatch: pytest.MonkeyPatch, events: list[tuple]
group = SimpleNamespace(get_metadata_builder=lambda _index: SimpleNamespace(reorder_batch_threshold=None))
return [[group], [group]], "cg-support", [4, 8]
# vLLM 0.29 dropped attn_groups and cache_dtype from init_kv_cache: the
# layout now rides on the resolved CacheConfig.kv_cache_layout instead.
def init_cache(
runner_kv_caches,
forward_context,
kv_cache_config,
attn_groups,
device,
cache_dtype,
kernel_block_sizes,
vllm_config,
):
events.append(("cache", kv_cache_config, attn_groups, kernel_block_sizes))
events.append(("cache", kv_cache_config, kernel_block_sizes))
runner_kv_caches.extend(["cache-0", "cache-1"])
return {"layer-0": "tensor-0", "layer-1": "tensor-1"}