mirror of
https://github.com/LostRuins/koboldcpp.git
synced 2026-05-22 11:16:08 +00:00
5ab5d5fb25
This PR improves q6_k_q8_k gemm kernel with arm64 i8mm instruction.
Tested on neoverse-n2 with llama3 8b q6_k quantization model.
- 40% ~ 54% S_PP uplift for all batch sizes
- 16% ~ 47% S_TG uplift for batch size 4 and above
Perplexity doesn't change with this PR.
```
// tested on neoverse-n2
$ llama-batched-bench \
-m Meta-Llama-3-8B-Instruct-Q6_K.gguf \
--no-mmap -fa \
-c 8192 -b 4096 -ub 512 -npp 128 -ntg 128 \
-npl 1,2,4,8,16,32 \
-t 64
---------------------------------------------------------------------
| PP | TG | B | S_PP t/s | S_TG t/s |
| | | | original | this pr | original | this pr |
|-------|--------|------|----------|----------|----------|----------|
| 128 | 128 | 1 | 78.52 | 109.18 | 18.63 | 18.88 |
| 128 | 128 | 2 | 84.62 | 123.94 | 34.54 | 36.92 |
| 128 | 128 | 4 | 84.36 | 122.49 | 52.65 | 61.32 |
| 128 | 128 | 8 | 90.52 | 138.87 | 63.46 | 84.41 |
| 128 | 128 | 16 | 90.11 | 138.56 | 71.04 | 101.33 |
| 128 | 128 | 32 | 89.81 | 137.79 | 75.14 | 110.47 |
---------------------------------------------------------------------
```
|
||
|---|---|---|
| .. | ||
| ggml-blas | ||
| ggml-cann | ||
| ggml-cpu | ||
| ggml-cuda | ||
| ggml-hip | ||
| ggml-kompute | ||
| ggml-metal | ||
| ggml-musa | ||
| ggml-opencl | ||
| ggml-rpc | ||
| ggml-sycl | ||
| ggml-vulkan | ||
| CMakeLists.txt | ||
| ggml-alloc.c | ||
| ggml-backend-impl.h | ||
| ggml-backend-reg.cpp | ||
| ggml-backend.cpp | ||
| ggml-common.h | ||
| ggml-impl.h | ||
| ggml-opt.cpp | ||
| ggml-quants.c | ||
| ggml-quants.h | ||
| ggml-threading.cpp | ||
| ggml-threading.h | ||
| ggml.c | ||
| gguf.cpp | ||