diff options
| author | Kawrakow <iwankawrakow@gmail.com> | 2025-02-06 14:08:52 +0200 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2025-02-06 14:08:52 +0200 |
| commit | 7f61b3068e18728e5e7e2b95546ff03dd2fd41ac (patch) | |
| tree | f175a942a6ebd2d2d8b08c46fa71d9f6fbad50e7 /include/llama.h | |
| parent | a6f9f2ec9af92b5a13f035db054aac2fd2efaee7 (diff) | |
IQ1_M_R4: better 1.75 bpw quants (#187)
* iq1_m_r4: basics (quantize/dequantize)
* iq1_m_r4: Zen4 gemm
* iq1_m_r4: neon gemm
* iq1_m_r4: switch to q8_0_x4 also on AVX2/Zen4
With the deltas being per group of 8, we cannot make use
of the q8 sums stored in q8_1, so we get a tiny gain by
using q8_0_x4.
* iq1_m_r4: rename mul_mat_iq1_m_r4_q8_1 to mul_mat_iq1_m_r4_q8_0
---------
Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
Diffstat (limited to 'include/llama.h')
| -rw-r--r-- | include/llama.h | 1 |
1 files changed, 1 insertions, 0 deletions
diff --git a/include/llama.h b/include/llama.h index 0f6d15ac..3f25b296 100644 --- a/include/llama.h +++ b/include/llama.h @@ -197,6 +197,7 @@ extern "C" { LLAMA_FTYPE_MOSTLY_IQ3_S_R4 = 226, // except 1d tensors LLAMA_FTYPE_MOSTLY_IQ2_M_R4 = 229, // except 1d tensors LLAMA_FTYPE_MOSTLY_IQ4_XS_R4 = 230, // except 1d tensors + LLAMA_FTYPE_MOSTLY_IQ1_M_R4 = 231, // except 1d tensors LLAMA_FTYPE_MOSTLY_Q6_0_R4 = 335, // except 1d tensors LLAMA_FTYPE_MOSTLY_BF16_R16 = 232, // except 1d tensors LLAMA_FTYPE_MOSTLY_IQ2_BN_R4 = 337, // except 1d tensors |