Mirrors/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/llama.cpp.git synced 2024-12-25 13:58:46 +01:00
Code Issues Packages Projects Releases Wiki Activity

llama : correct hparams comparison (#3446)

Browse Source 
* fixed floating point comparison issues

* updated implementation for hparam comparison to handle inf and NaN

* fixed code review comments

* minor simplification

* rename is_float_eq -> is_float_close

---------

Co-authored-by: Cebtenzzre <cebtenzzre@gmail.com>
This commit is contained in:
l3utterfly 2023-10-06 18:47:59 +08:00 committed by GitHub
parent 04b2f4386e
commit 16820a5a0d
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 39 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

40
llama.cpp
View File

@ -125,6 +125,27 @@ static void replace_all(std::string & s, const std::string & search, const std::
} }
s = std::move(result); s = std::move(result);
} }
static bool is_float_close(float a, float b, float abs_tol) {
// Check for non-negative tolerance
if (abs_tol < 0.0) {
throw std::invalid_argument("Tolerance must be non-negative");
}
// Exact equality check
if (a == b) {
return true;
}
// Check for infinities
if (std::isinf(a) || std::isinf(b)) {
return false;
}
// Regular comparison using the provided absolute tolerance
return std::fabs(b - a) <= abs_tol;
}
#ifdef GGML_USE_CPU_HBM #ifdef GGML_USE_CPU_HBM
#include <hbwmalloc.h> #include <hbwmalloc.h>
#endif #endif
@ -969,7 +990,24 @@ struct llama_hparams {
float rope_freq_scale_train; float rope_freq_scale_train;
bool operator!=(const llama_hparams & other) const { bool operator!=(const llama_hparams & other) const {
return static_cast<bool>(memcmp(this, &other, sizeof(llama_hparams))); // NOLINT if (this->vocab_only != other.vocab_only) return true;
if (this->n_vocab != other.n_vocab) return true;
if (this->n_ctx_train != other.n_ctx_train) return true;
if (this->n_embd != other.n_embd) return true;
if (this->n_head != other.n_head) return true;
if (this->n_head_kv != other.n_head_kv) return true;
if (this->n_layer != other.n_layer) return true;
if (this->n_rot != other.n_rot) return true;
if (this->n_ff != other.n_ff) return true;
const float EPSILON = 1e-9;
if (!is_float_close(this->f_norm_eps, other.f_norm_eps, EPSILON)) return true;
if (!is_float_close(this->f_norm_rms_eps, other.f_norm_rms_eps, EPSILON)) return true;
if (!is_float_close(this->rope_freq_base_train, other.rope_freq_base_train, EPSILON)) return true;
if (!is_float_close(this->rope_freq_scale_train, other.rope_freq_scale_train, EPSILON)) return true;
return false;
} }
uint32_t n_gqa() const { uint32_t n_gqa() const {