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 5, 04:45 UTC
[Bugfix][ROCm]: Allow `gpt_oss_mxfp4` quantization method on rocm (#39754)
Signed-off-by: Rohan138 <rohanpotdar138@gmail.com>
Rohan Potdar committed
Apr 14, 2026 at 10:10 UTC
23f3760217614807b1c1b08e593a54a824e42479
1 file changed
+1
vllm/platforms/rocm.py
+1
@@ -412,6 +412,7 @@ class RocmPlatform(Platform):
412
"gguf",
413
"quark",
414
"mxfp4",
415
+ "gpt_oss_mxfp4",
416
"torchao",
417
"bitsandbytes",
418
"modelopt_fp4",