@tduncan / Nvidia-Optimization-Stack-VLLM Mirror · read-only / commits / ee8217e5be
Fork 0

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 17, 06:45 UTC

Add Mistral to quantization model list (#1278)

amaleshvemula committed Oct 11, 2023 at 09:26 UTC ee8217e5bee5860469204ee57077a91138c9af02
1 file changed +1
vllm/model_executor/model_loader.py
+1
@@ -35,6 +35,7 @@ _MODEL_REGISTRY = {
35 # FIXME(woosuk): Remove this once all models support quantization.
36 _MODEL_CLASSES_SUPPORT_QUANTIZATION = [
37 LlamaForCausalLM,
38 + MistralForCausalLM,
39 ]
40
41