[ggerganov/llama.cpp]metal:修复 #2268 之后的构建错误和 rope kernel sig

2024-07-05 753 views
3

不确定其他人是如何编译的。在 M2 Ultra 上,MSL 代码中存在相当多的错误:

ggml_metal_init: allocating
ggml_metal_init: found device: Apple M2 Ultra
ggml_metal_init: picking default device: Apple M2 Ultra
ggml_metal_init: default.metallib not found, loading from source
ggml_metal_init: loading '/Users/ggerganov/development/github/llama.cpp/ggml-metal.metal'
ggml_metal_init: error: Error Domain=MTLLibraryErrorDomain Code=3 "program_source:1073:11: error: pointer type must have explicit address space qualifier
    float * cos_theta, float * sin_theta
          ^
program_source:1073:30: error: pointer type must have explicit address space qualifier
    float * cos_theta, float * sin_theta
                             ^
program_source:1079:9: error: use of undeclared identifier 'ramp_mix'
        ramp_mix = rope_yarn_ramp(corr_dims[0], corr_dims[1], i0) * ext_factor;
        ^
program_source:1080:37: error: use of undeclared identifier 'ramp_mix'
        theta = theta_interp * (1 - ramp_mix) + theta_extrap * ramp_mix;
                                    ^
program_source:1080:64: error: use of undeclared identifier 'ramp_mix'
        theta = theta_interp * (1 - ramp_mix) + theta_extrap * ramp_mix;
                                                               ^
program_source:1083:33: error: use of undeclared identifier 'logf'
        mscale *= 1.0f + 0.1f * logf(1.0f / freq_scale);
                                ^
program_source:1085:18: error: use of undeclared identifier 'cosf'
    *cos_theta = cosf(theta) * mscale;
                 ^
program_source:1086:18: error: use of undeclared identifier 'sinf'
    *sin_theta = sinf(theta) * mscale;
                 ^
program_source:1172:33: error: use of undeclared identifier 'n_orig_ctx'
    rope_yarn_corr_dims(n_dims, n_orig_ctx, freq_base, beta_fast, beta_slow, corr_dims);
                                ^
program_source:1223:57: error: explicit instantiation of 'kernel_rope' does not refer to a function template, variable template, member function, member class, or static data member
template [[host_name("kernel_rope_f32")]] kernel rope_t kernel_rope<float>;
                                                        ^
program_source:1133:13: note: candidate template ignored: could not match 'void (const device void *, const device int32_t *, device float *, const constant int64_t &, const constant int64_t &, const constant int64_t &, const constant int64_t &, const constant uint64_t &, const constant uint64_t &, const constant uint64_t &, const constant uint64_t &, const constant int64_t &, const constant int64_t &, const constant int64_t &, const constant int64_t &, const constant uint64_t &, const constant uint64_t &, const constant uint64_t &, const constant uint64_t &, const constant int &, const constant int &, const constant int &, const constant float &, const constant float &, const constant float &, const constant float &, const constant float &, const constant float &, uint, uint3, uint3)' (aka 'void (const device void *, const device int *, device float *, const constant long &, const constant long &, const constant long &, const constant long &, const constant unsigned long &, const constant unsigned long &, const constant unsigned long &, const constant unsigned long &, const constant long &, const constant long &, const constant long &, const constant long &, const constant unsigned long &, const constant unsigned long &, const constant unsigned long &, const constant unsigned long &, const constant int &, const constant int &, const constant int &, const constant float &, const constant float &, const constant float &, const constant float &, const constant float &, const constant float &, unsigned int, uint3, uint3)') against 'void (const device void *, const device int32_t *, device float *, const constant int64_t &, const constant int64_t &, const constant int64_t &, const constant int64_t &, const constant uint64_t &, const constant uint64_t &, const constant uint64_t &, const constant uint64_t &, const constant int64_t &, const constant int64_t &, const constant int64_t &, const constant int64_t &, const constant uint64_t &, const constant uint64_t &, const constant uint64_t &, const constant uint64_t &, const constant int &, const constant int &, const constant int &, const constant float &, const constant float &, uint, uint3, uint3)' (aka 'void (const device void *, const device int *, device float *, const constant long &, const constant long &, const constant long &, const constant long &, const constant unsigned long &, const constant unsigned long &, const constant unsigned long &, const constant unsigned long &, const constant long &, const constant long &, const constant long &, const constant long &, const constant unsigned long &, const constant unsigned long &, const constant unsigned long &, const constant unsigned long &, const constant int &, const constant int &, const constant int &, const constant float &, const constant float &, unsigned int, uint3, uint3)')
kernel void kernel_rope(
            ^
program_source:1224:57: error: explicit instantiation of 'kernel_rope' does not refer to a function template, variable template, member function, member class, or static data member
template [[host_name("kernel_rope_f16")]] kernel rope_t kernel_rope<half>;
                                                        ^
program_source:1133:13: note: candidate template ignored: could not match 'void (const device void *, const device int32_t *, device float *, const constant int64_t &, const constant int64_t &, const constant int64_t &, const constant int64_t &, const constant uint64_t &, const constant uint64_t &, const constant uint64_t &, const constant uint64_t &, const constant int64_t &, const constant int64_t &, const constant int64_t &, const constant int64_t &, const constant uint64_t &, const constant uint64_t &, const constant uint64_t &, const constant uint64_t &, const constant int &, const constant int &, const constant int &, const constant float &, const constant float &, const constant float &, const constant float &, const constant float &, const constant float &, uint, uint3, uint3)' (aka 'void (const device void *, const device int *, device float *, const constant long &, const constant long &, const constant long &, const constant long &, const constant unsigned long &, const constant unsigned long &, const constant unsigned long &, const constant unsigned long &, const constant long &, const constant long &, const constant long &, const constant long &, const constant unsigned long &, const constant unsigned long &, const constant unsigned long &, const constant unsigned long &, const constant int &, const constant int &, const constant int &, const constant float &, const constant float &, const constant float &, const constant float &, const constant float &, const constant float &, unsigned int, uint3, uint3)') against 'void (const device void *, const device int32_t *, device float *, const constant int64_t &, const constant int64_t &, const constant int64_t &, const constant int64_t &, const constant uint64_t &, const constant uint64_t &, const constant uint64_t &, const constant uint64_t &, const constant int64_t &, const constant int64_t &, const constant int64_t &, const constant int64_t &, const constant uint64_t &, const constant uint64_t &, const constant uint64_t &, const constant uint64_t &, const constant int &, const constant int &, const constant int &, const constant float &, const constant float &, uint, uint3, uint3)' (aka 'void (const device void *, const device int *, device float *, const constant long &, const constant long &, const constant long &, const constant long &, const constant unsigned long &, const constant unsigned long &, const constant unsigned long &, const constant unsigned long &, const constant long &, const constant long &, const constant long &, const constant long &, const constant unsigned long &, const constant unsigned long &, const constant unsigned long &, const constant unsigned long &, const constant int &, const constant int &, const constant int &, const constant float &, const constant float &, unsigned int, uint3, uint3)')
kernel void kernel_rope(
            ^
" UserInfo={NSLocalizedDescription=program_source:1073:11: error: pointer type must have explicit address space qualifier
    float * cos_theta, float * sin_theta
          ^
program_source:1073:30: error: pointer type must have explicit address space qualifier
    float * cos_theta, float * sin_theta
                             ^
program_source:1079:9: error: use of undeclared identifier 'ramp_mix'
        ramp_mix = rope_yarn_ramp(corr_dims[0], corr_dims[1], i0) * ext_factor;
        ^
program_source:1080:37: error: use of undeclared identifier 'ramp_mix'
        theta = theta_interp * (1 - ramp_mix) + theta_extrap * ramp_mix;
                                    ^
program_source:1080:64: error: use of undeclared identifier 'ramp_mix'
        theta = theta_interp * (1 - ramp_mix) + theta_extrap * ramp_mix;
                                                               ^
program_source:1083:33: error: use of undeclared identifier 'logf'
        mscale *= 1.0f + 0.1f * logf(1.0f / freq_scale);
                                ^
program_source:1085:18: error: use of undeclared identifier 'cosf'
    *cos_theta = cosf(theta) * mscale;
                 ^
program_source:1086:18: error: use of undeclared identifier 'sinf'
    *sin_theta = sinf(theta) * mscale;
                 ^
program_source:1172:33: error: use of undeclared identifier 'n_orig_ctx'
    rope_yarn_corr_dims(n_dims, n_orig_ctx, freq_base, beta_fast, beta_slow, corr_dims);
                                ^
program_source:1223:57: error: explicit instantiation of 'kernel_rope' does not refer to a function template, variable template, member function, member class, or static data member
template [[host_name("kernel_rope_f32")]] kernel rope_t kernel_rope<float>;
                                                        ^
program_source:1133:13: note: candidate template ignored: could not match 'void (const device void *, const device int32_t *, device float *, const constant int64_t &, const constant int64_t &, const constant int64_t &, const constant int64_t &, const constant uint64_t &, const constant uint64_t &, const constant uint64_t &, const constant uint64_t &, const constant int64_t &, const constant int64_t &, const constant int64_t &, const constant int64_t &, const constant uint64_t &, const constant uint64_t &, const constant uint64_t &, const constant uint64_t &, const constant int &, const constant int &, const constant int &, const constant float &, const constant float &, const constant float &, const constant float &, const constant float &, const constant float &, uint, uint3, uint3)' (aka 'void (const device void *, const device int *, device float *, const constant long &, const constant long &, const constant long &, const constant long &, const constant unsigned long &, const constant unsigned long &, const constant unsigned long &, const constant unsigned long &, const constant long &, const constant long &, const constant long &, const constant long &, const constant unsigned long &, const constant unsigned long &, const constant unsigned long &, const constant unsigned long &, const constant int &, const constant int &, const constant int &, const constant float &, const constant float &, const constant float &, const constant float &, const constant float &, const constant float &, unsigned int, uint3, uint3)') against 'void (const device void *, const device int32_t *, device float *, const constant int64_t &, const constant int64_t &, const constant int64_t &, const constant int64_t &, const constant uint64_t &, const constant uint64_t &, const constant uint64_t &, const constant uint64_t &, const constant int64_t &, const constant int64_t &, const constant int64_t &, const constant int64_t &, const constant uint64_t &, const constant uint64_t &, const constant uint64_t &, const constant uint64_t &, const constant int &, const constant int &, const constant int &, const constant float &, const constant float &, uint, uint3, uint3)' (aka 'void (const device void *, const device int *, device float *, const constant long &, const constant long &, const constant long &, const constant long &, const constant unsigned long &, const constant unsigned long &, const constant unsigned long &, const constant unsigned long &, const constant long &, const constant long &, const constant long &, const constant long &, const constant unsigned long &, const constant unsigned long &, const constant unsigned long &, const constant unsigned long &, const constant int &, const constant int &, const constant int &, const constant float &, const constant float &, unsigned int, uint3, uint3)')
kernel void kernel_rope(
            ^
program_source:1224:57: error: explicit instantiation of 'kernel_rope' does not refer to a function template, variable template, member function, member class, or static data member
template [[host_name("kernel_rope_f16")]] kernel rope_t kernel_rope<half>;
                                                        ^
program_source:1133:13: note: candidate template ignored: could not match 'void (const device void *, const device int32_t *, device float *, const constant int64_t &, const constant int64_t &, const constant int64_t &, const constant int64_t &, const constant uint64_t &, const constant uint64_t &, const constant uint64_t &, const constant uint64_t &, const constant int64_t &, const constant int64_t &, const constant int64_t &, const constant int64_t &, const constant uint64_t &, const constant uint64_t &, const constant uint64_t &, const constant uint64_t &, const constant int &, const constant int &, const constant int &, const constant float &, const constant float &, const constant float &, const constant float &, const constant float &, const constant float &, uint, uint3, uint3)' (aka 'void (const device void *, const device int *, device float *, const constant long &, const constant long &, const constant long &, const constant long &, const constant unsigned long &, const constant unsigned long &, const constant unsigned long &, const constant unsigned long &, const constant long &, const constant long &, const constant long &, const constant long &, const constant unsigned long &, const constant unsigned long &, const constant unsigned long &, const constant unsigned long &, const constant int &, const constant int &, const constant int &, const constant float &, const constant float &, const constant float &, const constant float &, const constant float &, const constant float &, unsigned int, uint3, uint3)') against 'void (const device void *, const device int32_t *, device float *, const constant int64_t &, const constant int64_t &, const constant int64_t &, const constant int64_t &, const constant uint64_t &, const constant uint64_t &, const constant uint64_t &, const constant uint64_t &, const constant int64_t &, const constant int64_t &, const constant int64_t &, const constant int64_t &, const constant uint64_t &, const constant uint64_t &, const constant uint64_t &, const constant uint64_t &, const constant int &, const constant int &, const constant int &, const constant float &, const constant float &, uint, uint3, uint3)' (aka 'void (const device void *, const device int *, device float *, const constant long &, const constant long &, const constant long &, const constant long &, const constant unsigned long &, const constant unsigned long &, const constant unsigned long &, const constant unsigned long &, const constant long &, const constant long &, const constant long &, const constant long &, const constant unsigned long &, const constant unsigned long &, const constant unsigned long &, const constant unsigned long &, const constant int &, const constant int &, const constant int &, const constant float &, const constant float &, unsigned int, uint3, uint3)')
kernel void kernel_rope(
            ^
}

回答

1

当我尝试量化 llama2 模型时,也出现了错误,尽管它使用的是旧版本的代码库:

[ 1/ 723] token_embd.weight - [ 8192, 32000, 1, 1], type = f16, quantizing to q4_K .. zsh: illegal hardware instruction

5

您最近升级到 Sonoma 了吗?

自从我升级后,K-quants 就一直这样对我。这种崩溃只发生在 Release (-O3) 版本中。Debug 和 -O2 工作正常。添加打印来调试这个可以让问题消失。所以我不知道如何修复它

我认为编译器出了问题。如果你能给我展示一个可以正常工作的提交,我会看看。但目前我不认为这是llama.cpp相关问题

3

感谢这个 PR。我最近第一次克隆了这个项目,遇到了这个问题。我以为我在构建时一定做错了什么!我再次拉动,make clean; make现在它运行正常了。

6

是的,这就是我们在这里所做的——我们在生产中进行测试?

7

我昨天在运行 macOS 13.6 的 M1 Max 上遇到了同样的问题,可以确认这里也已修复。

0

当我最初编写此代码时,我不得不请求朋友的朋友远程访问他的(Intel)Mac,以便我可以验证我的语法是否正确。

公司给我配了一台 M2 Macbook,所以我将来应该能够写出更好的 Metal 代码。

对于造成的所有损坏,您感到抱歉吗?

1

我公司给我配了一台 M2 Macbook

呃..应该买新款 M3 Macbook :)

6

啊,是的,我最近刚刚升级。如果它能与输入的打印消息配合使用,那么也许这就是解决方案……?