diff options
| author | Kawrakow <48489457+ikawrakow@users.noreply.github.com> | 2024-01-30 15:14:12 +0200 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2024-01-30 15:14:12 +0200 |
| commit | f4d7e5497485ce6ce0e322533930b7da4657dd2d (patch) | |
| tree | 78b30048cb4a9c78d5cf3e231a1ac3e9ed190577 /tests/test-backend-ops.cpp | |
| parent | 2256f36b79a932a478d4dcdf02c1e5a60056e5f3 (diff) | |
SOTA 3-bit quants (#5196)
* iq3_xxs: quantize/dequantize
RMSE seems a bit high-ish at about half-way between q2_K and
q3_K, so need to check more.
* iq3_xxs: CUDA dequantize works
* iq2_xxs: tuning quantization
* iq3_xxs: starting to look better
PPL on wiki.test.raw
LLaMA-v1-7B: 6.4218
LLaMA-v2-7B: 6.3560
Mistral-7B : 6.0717
This is better than Q3_K_XS, with a 5% reduction in quantized model
size.
* iq3_xxs: CUDA dot product
We have
PP-512: 5891 t/s
TG-128: 143.9 t/s
* iq3_xxs: scalar and AVX2 dot products
* iq3_xxs: ARM_NEON and Metal
Metal performance is decent, ARM_NEON is pathetic
* iq3_xxs: slightly better grid points
* Faster iq3_xxs and iq2_xs dot products on CUDA
* iq3_xxs: add some quant mix
* iq3_xxs: fix failing quantization test
Dot product still fails. Is this real?
* iq3_xxs: hopefully fix ROCm
* iq3_xxs: failing tests
This time the dot product accuracy did find an actual bug
in the AVX2 implementation.
* Add IQ3_XXS to test-backend-ops
---------
Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
Diffstat (limited to 'tests/test-backend-ops.cpp')
| -rw-r--r-- | tests/test-backend-ops.cpp | 1 |
1 files changed, 1 insertions, 0 deletions
diff --git a/tests/test-backend-ops.cpp b/tests/test-backend-ops.cpp index 775147d4..b328b19b 100644 --- a/tests/test-backend-ops.cpp +++ b/tests/test-backend-ops.cpp @@ -1890,6 +1890,7 @@ static bool test_backend(ggml_backend_t backend, test_mode mode, const char * op GGML_TYPE_Q4_K, GGML_TYPE_Q5_K, GGML_TYPE_Q6_K, GGML_TYPE_IQ2_XXS, GGML_TYPE_IQ2_XS, + GGML_TYPE_IQ3_XXS, }; // unary ops |