ikawrakow/ik_llama.cpp
1
0
Fork 0
mirror of https://github.com/ikawrakow/ik_llama.cpp.git synced 2026-02-26 16:14:10 +00:00
Code Issues Packages Projects Releases Wiki Activity

iq2_tn: TriLM specific 2.0625 bpw quantization

Browse Source 
Quantize/dequantize/scale dot product.

I get 46 t/s for the TriLM-3.9B with any SIMD!
Finally a compiler doing a decent job auto-vectorizing the
scalar implementation.
This commit is contained in:
Iwan Kawrakow
2024-08-05 14:22:05 +03:00
parent b409c15363
commit 1b41d792ec
9 changed files with 157 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

9
src/llama.cpp
View File

@@ -3759,6 +3759,7 @@ struct llama_model_loader {
case GGML_TYPE_IQ1_M: ftype = LLAMA_FTYPE_MOSTLY_IQ1_M; break;
case GGML_TYPE_IQ1_BN: ftype = LLAMA_FTYPE_MOSTLY_IQ1_BN; break;
case GGML_TYPE_IQ2_BN: ftype = LLAMA_FTYPE_MOSTLY_IQ2_BN; break;
case GGML_TYPE_IQ2_TN: ftype = LLAMA_FTYPE_MOSTLY_IQ2_TN; break;
case GGML_TYPE_IQ4_NL: ftype = LLAMA_FTYPE_MOSTLY_IQ4_NL; break;
case GGML_TYPE_IQ4_XS: ftype = LLAMA_FTYPE_MOSTLY_IQ4_XS; break;
case GGML_TYPE_IQ2_K: ftype = LLAMA_FTYPE_MOSTLY_IQ2_K; break;
@@ -4471,6 +4472,7 @@ static std::string llama_model_ftype_name(llama_ftype ftype) {
case LLAMA_FTYPE_MOSTLY_Q4_0_8_8: return "Q4_0_8_8";
case LLAMA_FTYPE_MOSTLY_IQ1_BN: return "IQ1_BN - 1.625 bpw Bitnet";
case LLAMA_FTYPE_MOSTLY_IQ2_BN: return "IQ2_BN - 2.00 bpw Bitnet";
case LLAMA_FTYPE_MOSTLY_IQ2_TN: return "IQT_BN - 2.06 bpw TriLM";
default: return "unknown, may not work";
}
@@ -15437,6 +15439,9 @@ static ggml_type llama_tensor_get_type(quantize_state_internal & qs, ggml_type n
else if (ftype == LLAMA_FTYPE_MOSTLY_IQ1_BN || ftype == LLAMA_FTYPE_MOSTLY_IQ2_BN) {
new_type = GGML_TYPE_IQ4_NL;
}
else if (ftype == LLAMA_FTYPE_MOSTLY_IQ2_TN) {
new_type = GGML_TYPE_Q4_K;
}
else if (new_type == GGML_TYPE_Q4_0_4_4 || new_type == GGML_TYPE_Q4_0_4_8 ||
new_type == GGML_TYPE_Q4_0_8_8) {
new_type = GGML_TYPE_Q4_0;
@@ -15640,7 +15645,7 @@ static ggml_type llama_tensor_get_type(quantize_state_internal & qs, ggml_type n
new_type == GGML_TYPE_IQ2_XS || new_type == GGML_TYPE_IQ2_XXS || new_type == GGML_TYPE_IQ2_S ||
new_type == GGML_TYPE_IQ3_XXS || new_type == GGML_TYPE_IQ1_S || new_type == GGML_TYPE_IQ3_S ||
new_type == GGML_TYPE_IQ1_M || new_type == GGML_TYPE_IQ4_K || new_type == GGML_TYPE_IQ2_K ||
new_type == GGML_TYPE_IQ5_K || new_type == GGML_TYPE_IQ3_K) {
new_type == GGML_TYPE_IQ5_K || new_type == GGML_TYPE_IQ3_K || new_type == GGML_TYPE_IQ2_TN) {
int nx = tensor->ne[0];
int ny = tensor->ne[1];
if (nx % QK_K != 0) {
@@ -15665,6 +15670,7 @@ static ggml_type llama_tensor_get_type(quantize_state_internal & qs, ggml_type n
case GGML_TYPE_IQ3_S:
case GGML_TYPE_IQ1_S:
case GGML_TYPE_IQ1_M:
case GGML_TYPE_IQ2_TN:
case GGML_TYPE_Q2_K:
case GGML_TYPE_Q3_K:
case GGML_TYPE_IQ2_K:
@@ -15773,6 +15779,7 @@ static void llama_model_quantize_internal(const std::string & fname_inp, const s
case LLAMA_FTYPE_MOSTLY_IQ1_M: default_type = GGML_TYPE_IQ1_M; break;
case LLAMA_FTYPE_MOSTLY_IQ1_BN: default_type = GGML_TYPE_IQ1_BN; break;
case LLAMA_FTYPE_MOSTLY_IQ2_BN: default_type = GGML_TYPE_IQ2_BN; break;
case LLAMA_FTYPE_MOSTLY_IQ2_TN: default_type = GGML_TYPE_IQ2_TN; break;
case LLAMA_FTYPE_MOSTLY_IQ4_NL: default_type = GGML_TYPE_IQ4_NL; break;
case LLAMA_FTYPE_MOSTLY_IQ4_XS: default_type = GGML_TYPE_IQ4_XS; break;
case LLAMA_FTYPE_MOSTLY_IQ2_K: default_type = GGML_TYPE_IQ2_K; break;