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 9, 12:30 UTC
[Bugfix] Fix display error (inconsistent with context) (#33020)
Signed-off-by: linhaifeng <1371675203@qq.com>
linhaifeng committed
Jan 28, 2026 at 04:33 UTC
f5d7049cc119e9bc572f29267e270b82a39d6ec1
1 file changed
+2
-2
vllm/engine/arg_utils.py
+2
-2
@@ -1951,13 +1951,13 @@ class EngineArgs:
1951
CpuArchEnum.RISCV,
1952
):
1953
logger.info(
1954
- "Chunked prefill is not supported for ARM and POWER, "
1954
+ "Chunked prefill is not supported for POWER, "
1955
"S390X and RISC-V CPUs; "
1956
"disabling it for V1 backend."
1957
)
1958
self.enable_chunked_prefill = False
1959
logger.info(
1960
- "Prefix caching is not supported for ARM and POWER, "
1960
+ "Prefix caching is not supported for POWER, "
1961
"S390X and RISC-V CPUs; "
1962
"disabling it for V1 backend."
1963
)