A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 4, 03:45 UTC
[Bugifx] Missing Renderer for `fastokens` mode (#41984)
Signed-off-by: tjtanaa <tunjian.tan@embeddedllm.com> Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>
TJian committed
May 8, 2026 at 14:45 UTC
445d747434542741340e62ff8f1c3a1b2b3d71c2
1 file changed
+2
-1
vllm/renderers/registry.py
+2
-1
@@ -22,8 +22,9 @@ logger = init_logger(__name__)
22
_VLLM_RENDERERS = {
23
"deepseek_v32": ("deepseek_v32", "DeepseekV32Renderer"),
24
"deepseek_v4": ("deepseek_v4", "DeepseekV4Renderer"),
25
- "hf": ("hf", "HfRenderer"),
25
+ "fastokens": ("hf", "HfRenderer"),
26
"grok2": ("grok2", "Grok2Renderer"),
27
+ "hf": ("hf", "HfRenderer"),
28
"kimi_audio": ("hf", "HfRenderer"),
29
"mistral": ("mistral", "MistralRenderer"),
30
"qwen_vl": ("hf", "HfRenderer"),