vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Merge branch 'master' into ik/fix_kernel_norm

Browse source
This commit is contained in:
Georgi Gerganov 2023-09-07 16:39:38 +03:00 • committed by GitHub
commit 7d6fac3f18
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
2 changed files with 1 additions and 3 deletions
Download patch file Download diff file Expand all files Collapse all files

2
common/common.cpp
View file

@ -773,7 +773,7 @@ std::tuple<struct llama_model *, struct llama_context *> llama_init_from_gpt_par
LOG("warming up the model with an empty run\n");
const std::vector<llama_token> tmp = { llama_token_bos(lctx), llama_token_eos(lctx), };
llama_eval(lctx, tmp.data(), tmp.size(), 0, params.n_threads);
llama_eval(lctx, tmp.data(), std::min(tmp.size(), (size_t) params.n_batch), 0, params.n_threads);
llama_reset_timings(lctx);
}

2
ggml-metal.metal
View file

@ -247,7 +247,6 @@ kernel void kernel_norm(
}
}
kernel void kernel_rms_norm(
device const void * src0,
device float * dst,
@ -615,7 +614,6 @@ kernel void kernel_mul_mat_f16_f32(
}
}
}
}
kernel void kernel_alibi_f32(