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 7, 00:15 UTC
[Misc] fix typo: dependant -> dependent (2 lines change) (#36511)
Signed-off-by: SoluMilken <ypiheyn.imm02g@g2.nctu.edu.tw>
SoluMilken committed
Mar 10, 2026 at 01:00 UTC
55d27cca55310a04fb82c90d26a5afed90f01de7
2 files changed
+2
-2
vllm/engine/arg_utils.py
+1
-1
@@ -2204,7 +2204,7 @@ class AsyncEngineArgs(EngineArgs):
2204
"--enable-log-requests",
2205
action=argparse.BooleanOptionalAction,
2206
default=AsyncEngineArgs.enable_log_requests,
2207
- help="Enable logging request information, dependant on log level:\n"
2207
+ help="Enable logging request information, dependent on log level:\n"
2208
"- INFO: Request ID, parameters and LoRA request.\n"
2209
"- DEBUG: Prompt inputs (e.g: text, token IDs).\n"
2210
"You can set the minimum log level via `VLLM_LOGGING_LEVEL`.",
vllm/model_executor/models/qwen3_next.py
+1
-1
@@ -441,7 +441,7 @@ class Qwen3NextGatedDeltaNet(nn.Module, MambaBase):
441
},
442
)
443
444
- # selective projection used to make dt, B and C input dependant
444
+ # selective projection used to make dt, B and C input dependent
445
446
# time step projection (discretization)
447
# instantiate once and copy inv_dt in init_weights of PretrainedModel