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 7, 22:45 UTC
[Doc] Fix example of eagle3 (#34960)
Signed-off-by: Petr Pechman <petr.pechman@firma.seznam.cz> Co-authored-by: Petr Pechman <petr.pechman@firma.seznam.cz>
petrpechman committed
Feb 21, 2026 at 10:57 UTC
bebfe55b1c17c2e0fedb1b402df1dddfc1a04684
1 file changed
+1
-1
docs/features/speculative_decoding/eagle.md
+1
-1
@@ -44,7 +44,7 @@ llm = LLM(
44
"model": "RedHatAI/Llama-3.1-8B-Instruct-speculator.eagle3",
45
"draft_tensor_parallel_size": 2,
46
"num_speculative_tokens": 2,
47
- "method": "eagle",
47
+ "method": "eagle3",
48
},
49
)
50