Deprecated 1st generation Qwen and QwenVL models (#45131)

Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
This commit is contained in:
Harry Mellor
2026-06-10 14:55:33 +00:00
committed by GitHub
parent ccc05de038
commit 3cc9fecd58
27 changed files with 6 additions and 1349 deletions
+1 -1
View File
@@ -686,7 +686,7 @@ environment_variables: dict[str, Callable[[], Any]] = {
# If true, replace the Rust BPE backend that powers HF fast tokenizers
# with the `fastokens` (https://github.com/crusoecloud/fastokens) shim.
# Applies to any tokenizer mode that loads an HF fast tokenizer
# (`hf`, `deepseek_v32`, `deepseek_v4`, `qwen_vl`, …). The `fastokens`
# (`hf`, `deepseek_v32`, `deepseek_v4`, …). The `fastokens`
# Python package must be installed.
"VLLM_USE_FASTOKENS": lambda: bool(int(os.getenv("VLLM_USE_FASTOKENS", "0"))),
# Interval in seconds to log a warning message when the ring buffer is full