llm.c的Makefile

源码

CC ?= clang
CFLAGS = -Ofast -Wno-unused-result -Wno-ignored-pragmas -Wno-unknown-attributes
LDFLAGS =
LDLIBS = -lm
INCLUDES =
CFLAGS_COND = -march=native

# Find nvcc
SHELL_UNAME = $(shell uname)
REMOVE_FILES = rm -f
OUTPUT_FILE = -o $@
CUDA_OUTPUT_FILE = -o $@

# NVCC flags
# -t=0 is short for --threads, 0 = number of CPUs on the machine
NVCC_FLAGS = -O3 -t=0 --use_fast_math
NVCC_LDFLAGS = -lcublas -lcublasLt
NVCC_INCLUDES =
NVCC_LDLIBS =
NCLL_INCUDES =
NVCC_CUDNN =
# overridable flag for multi-GPU training. by default we won't build with cudnn
# because it bloats up the compile time from a few seconds to ~minute
US
评论 2
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包

打赏作者

109702008

你的鼓励将是我创作的最大动力

¥1 ¥2 ¥4 ¥6 ¥10 ¥20
扫码支付:¥1
获取中
扫码支付

您的余额不足,请更换扫码支付或充值

打赏作者

实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值