Deprecations for v0.23 and v0.24 (#44992)

Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
This commit is contained in:
Harry Mellor
2026-06-11 14:35:38 +00:00
committed by GitHub
parent 55911db580
commit 03878d1c22
35 changed files with 100 additions and 674 deletions
+1 -3
View File
@@ -1585,7 +1585,6 @@ def test_unquantized_bf16_flashinfer_trtllm_backend(
e: int,
topk: int,
dtype: torch.dtype,
monkeypatch,
workspace_init,
):
"""
@@ -1593,8 +1592,6 @@ def test_unquantized_bf16_flashinfer_trtllm_backend(
"""
set_random_seed(7)
monkeypatch.setenv("VLLM_USE_FLASHINFER_MOE_FP16", "1")
from vllm.model_executor.layers.fused_moe.config import (
FusedMoEConfig,
FusedMoEParallelConfig,
@@ -1626,6 +1623,7 @@ def test_unquantized_bf16_flashinfer_trtllm_backend(
in_dtype=dtype,
routing_method=RoutingMethodType.Renormalize,
max_num_tokens=next_power_of_2(m),
moe_backend="flashinfer_trtllm",
)
with set_current_vllm_config(vllm_config):