diff options
Diffstat (limited to 'examples')
| -rw-r--r-- | examples/llama-bench/llama-bench.cpp | 3 | ||||
| -rw-r--r-- | examples/quantize/quantize.cpp | 2 |
2 files changed, 5 insertions, 0 deletions
diff --git a/examples/llama-bench/llama-bench.cpp b/examples/llama-bench/llama-bench.cpp index 95df06dc..0222c213 100644 --- a/examples/llama-bench/llama-bench.cpp +++ b/examples/llama-bench/llama-bench.cpp @@ -339,6 +339,9 @@ static ggml_type ggml_type_from_name(const std::string & s) { if (s == "q6_0") { return GGML_TYPE_Q6_0; } + if (s == "q8_KV") { + return GGML_TYPE_Q8_KV; + } return GGML_TYPE_COUNT; } diff --git a/examples/quantize/quantize.cpp b/examples/quantize/quantize.cpp index 7ceee208..916f57ec 100644 --- a/examples/quantize/quantize.cpp +++ b/examples/quantize/quantize.cpp @@ -56,6 +56,7 @@ static const std::vector<struct quant_option> QUANT_OPTIONS = { { "Q5_0_R4", LLAMA_FTYPE_MOSTLY_Q5_0_R4, " 5.50 bpw quantization", }, { "Q6_0_R4", LLAMA_FTYPE_MOSTLY_Q6_0_R4, " 6.50 bpw quantization", }, { "Q8_0_R8", LLAMA_FTYPE_MOSTLY_Q8_0_R8, " 8.50 bpw quantization", }, + { "Q8_KV", LLAMA_FTYPE_MOSTLY_Q8_KV, " 8.00 bpw quantization", }, { "IQ4_XS", LLAMA_FTYPE_MOSTLY_IQ4_XS, " 4.25 bpw non-linear quantization", }, { "IQ4_KS", LLAMA_FTYPE_MOSTLY_IQ4_KS, " 4.25 bpw non-linear quantization", }, { "IQ4_KS_R4",LLAMA_FTYPE_MOSTLY_IQ4_KS_R4,"IQ4_KS repacked", }, @@ -82,6 +83,7 @@ static const std::vector<struct quant_option> QUANT_OPTIONS = { { "Q6_K", LLAMA_FTYPE_MOSTLY_Q6_K, " 5.15G, +0.0008 ppl @ LLaMA-v1-7B", }, { "Q6_K_R4", LLAMA_FTYPE_MOSTLY_Q6_K_R4, "Q6_K repacked", }, { "Q8_K_R8", LLAMA_FTYPE_MOSTLY_Q8_K_R8, "Q8_K repacked", }, + { "Q8_KV_R8", LLAMA_FTYPE_MOSTLY_Q8_KV_R8, "Q8_KV repacked", }, { "Q8_0", LLAMA_FTYPE_MOSTLY_Q8_0, " 6.70G, +0.0004 ppl @ LLaMA-v1-7B", }, { "Q4_0_4_4", LLAMA_FTYPE_MOSTLY_Q4_0_4_4, " 4.34G, +0.4685 ppl @ Llama-3-8B", }, { "Q4_0_4_8", LLAMA_FTYPE_MOSTLY_Q4_0_4_8, " 4.34G, +0.4685 ppl @ Llama-3-8B", }, |