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, 00:00 UTC
Fix mypy failure on main (#42197)
Signed-off-by: Mohammad Miadh Angkad <MAngkad.BSDSBA2027@aim.edu>
Mohammad Miadh Angkad committed
May 10, 2026 at 15:55 UTC
efd0e7789d879188a1e64a07b47a8d20fd97129e
1 file changed
+1
tests/compile/correctness_e2e/test_sequence_parallel.py
+1
@@ -435,6 +435,7 @@ def test_tp_sp_nvfp4_generation(num_gpus_available: int):
435
num_gpus_available,
436
use_inductor_graph_partition=False,
437
fuse_gemm_comms=False,
438
+ enable_prompt_embeds=False,
439
method="generate",
440
is_multimodal=False,
441
dtype="bfloat16",