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 15, 22:15 UTC
[ci] Fix spec decode test (#13600)
Kevin H. Luu committed
Feb 20, 2025 at 00:56 UTC
aa1e62d0dbfcdbea66f497d0b281fd96dd402246
1 file changed
-1
tests/conftest.py
-1
@@ -57,7 +57,6 @@ MODELS_ON_S3 = [
57
"ArthurZ/Ilama-3.2-1B",
58
"llava-hf/llava-1.5-7b-hf",
59
"TinyLlama/TinyLlama-1.1B-Chat-v1.0",
60
- "JackFram/llama-160m",
60
"ai21labs/Jamba-tiny-random",
61
"neuralmagic/Meta-Llama-3-8B-Instruct-FP8-KV",
62
"nm-testing/Phi-3-mini-128k-instruct-FP8",