You cannot select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
llama.cpp/examples
Georgi Gerganov 77a73403ca
ggml : add new Q4_2 quantization (ARM only) (#1046)
* ggml : Q4_2 ARM

* ggml : add ggml_is_quantized()

* llama : update llama_type_name() with Q4_2 entry

* ggml : speed-up q4_2

- 4 threads: ~100ms -> ~90ms
- 8 threads:  ~55ms -> ~50ms

* ggml : optimize q4_2 using vmlaq_n_f32 + vmulq_n_f32
1 year ago
..
benchmark benchmark : fix result validation in benchmark-q4_0-matmult (#987) 1 year ago
embedding examples: add missing <ctime> include for time() (#1011) 1 year ago
main Add LoRA support (#820) 1 year ago
perplexity Add LoRA support (#820) 1 year ago
quantize ggml : add new Q4_2 quantization (ARM only) (#1046) 1 year ago
quantize-stats quantize-stats : fix bug in --type argument 1 year ago
CMakeLists.txt Add quantize-stats command for testing quantization (#728) 1 year ago
Miku.sh Fix whitespace, add .editorconfig, add GitHub workflow (#883) 1 year ago
alpaca.sh examples : add -n to alpaca and gpt4all scripts (#706) 1 year ago
chat-13B.bat Create chat-13B.bat (#592) 1 year ago
chat-13B.sh Move chat scripts into "./examples" 1 year ago
chat.sh If n_predict == -1, generate forever 1 year ago
common.cpp Add LoRA support (#820) 1 year ago
common.h Add LoRA support (#820) 1 year ago
gpt4all.sh examples : add -n to alpaca and gpt4all scripts (#706) 1 year ago
reason-act.sh add example of re-act pattern (#583) 1 year ago