[Rebase] Rebase to vllm 0.27.0 (#5976)

Signed-off-by: tzhouam <tzhouam@connect.ust.hk>
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
This commit is contained in:
Zhou TaichangandClaude Opus 5 authored and GitHub committed 2026-08-11 15:23:46 +00:00
1 parent 584d78c673
commit 2ce15ab7a0
55 files changed
+1335 -93

No files matched your search

+14
View File
@@ -137,3 +137,17 @@ def reinit_rotary_inv_freq(
inv_freq.copy_(new_inv_freq.to(dtype=inv_freq.dtype))
n_fixed += 1
return n_fixed
def is_interleaved(config) -> bool:
"""Detect if the model with this config is used with interleaved attention.
Replicates the helper that was removed from upstream
``vllm.transformers_utils.config`` (vLLM commit 26d725c334,
"[Model] Add VaultGemma via Transformers modeling backend") so models
that still need the check can share one copy.
"""
text_config = config.get_text_config()
if layer_types := getattr(text_config, "layer_types", None):
return len(set(layer_types)) > 1
return False