diff options
| author | Kawrakow <48489457+ikawrakow@users.noreply.github.com> | 2024-01-11 20:39:39 +0100 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2024-01-11 21:39:39 +0200 |
| commit | 49662cbed3e95f5976c070b85b9fd53fd577038d (patch) | |
| tree | b70cd0956715bc11696f6e47d26788e24c5112c4 /llama.cpp | |
| parent | 3ba5b8ca8e6181a5c712c5b77595a29f1d3e2b97 (diff) | |
ggml : SOTA 2-bit quants (add IQ2_XS) (#4856)
* iq2_xs: basics
* iq2_xs: this should have been in the basics
* iq2_xs: CUDA and scalar CPU works
* iq2_xs: WIP Metal
* iq2_xs: Metal now works
* iq2_xs: working, but dog slow, ARM_NEON dot product
* iq2_xs: better ARM_NEON dot product
We are now at 19.5 t/s for TG-128 and 61 t/s for PP-512 when
running on the CPU.
* iq2_xs: AVX2 dot product - 19.5 t/s
* iq2_xs: faster AVX2 dit product
21.4 t/s for TG-128, 59.2 t/s for PP-512.
The latter is 2x compared to the previous version.
* iq2_xs: had forgotten to delete iq2-data.h
* Add llama enum for IQ2_XS
---------
Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
Diffstat (limited to 'llama.cpp')
| -rw-r--r-- | llama.cpp | 3 |
1 files changed, 3 insertions, 0 deletions
@@ -2223,6 +2223,7 @@ struct llama_model_loader { case GGML_TYPE_Q5_K: ftype = LLAMA_FTYPE_MOSTLY_Q5_K_M; break; case GGML_TYPE_Q6_K: ftype = LLAMA_FTYPE_MOSTLY_Q6_K; break; case GGML_TYPE_IQ2_XXS: ftype = LLAMA_FTYPE_MOSTLY_IQ2_XXS; break; + case GGML_TYPE_IQ2_XS: ftype = LLAMA_FTYPE_MOSTLY_IQ2_XS; break; default: { LLAMA_LOG_WARN("%s: unknown type %s\n", __func__, ggml_type_name(type_max)); @@ -2595,6 +2596,7 @@ static std::string llama_model_ftype_name(llama_ftype ftype) { case LLAMA_FTYPE_MOSTLY_Q5_K_M: return "Q5_K - Medium"; case LLAMA_FTYPE_MOSTLY_Q6_K: return "Q6_K"; case LLAMA_FTYPE_MOSTLY_IQ2_XXS:return "IQ2_XSS - 2.0625 bpw"; + case LLAMA_FTYPE_MOSTLY_IQ2_XS: return "IQ2_XS - 2.3125 bpw"; default: return "unknown, may not work"; } @@ -9050,6 +9052,7 @@ static void llama_model_quantize_internal(const std::string & fname_inp, const s case LLAMA_FTYPE_MOSTLY_Q5_K_M: quantized_type = GGML_TYPE_Q5_K; break; case LLAMA_FTYPE_MOSTLY_Q6_K: quantized_type = GGML_TYPE_Q6_K; break; case LLAMA_FTYPE_MOSTLY_IQ2_XXS:quantized_type = GGML_TYPE_IQ2_XXS; break; + case LLAMA_FTYPE_MOSTLY_IQ2_XS :quantized_type = GGML_TYPE_IQ2_XS; break; default: throw std::runtime_error(format("invalid output file type %d\n", ftype)); } |