docs: fix tokenizer optimization typo (#44066)
Signed-off-by: chunyang.wen <chunyang.wen@gmail.com>
This commit is contained in:
@@ -296,7 +296,7 @@ llm = LLM(model="Qwen/Qwen3-8B")
|
|||||||
The `fastokens` Python package (>= 0.2.0) must be installed; if it isn't,
|
The `fastokens` Python package (>= 0.2.0) must be installed; if it isn't,
|
||||||
vLLM raises a clear `ImportError` at tokenizer load. The override applies to
|
vLLM raises a clear `ImportError` at tokenizer load. The override applies to
|
||||||
any `--tokenizer-mode` that ends up loading an HF fast tokenizer (`hf`,
|
any `--tokenizer-mode` that ends up loading an HF fast tokenizer (`hf`,
|
||||||
`deepseek_v32`, `deepseek_v4`, `qwen_vl`, …). Modes that don't use the HF
|
`deepseek_v32`, `deepseek_v4`, `qwen_vl`, …). Models that don't use the HF
|
||||||
fast tokenizer (`mistral`, `grok2`, `kimi_audio`) ignore the flag.
|
fast tokenizer (`mistral`, `grok2`, `kimi_audio`) ignore the flag.
|
||||||
|
|
||||||
Tokenizer-bound workloads — long shared prefixes, bursty short prompts,
|
Tokenizer-bound workloads — long shared prefixes, bursty short prompts,
|
||||||
|
|||||||
Reference in New Issue
Block a user