rwkv.cpp/rwkv
YorkZero 241350fde6
Feature add cublas support (#65)
* chore: add ggml import in the head of rwkv.h

* chore: add ggml import in the head of rwkv.h

* feat: add cublas support

* feat: update rwkv.cpp

* feat: remove unused change

* chore: fix linux build issue

* chore: sync ggml and offload tensor to gpu

* chore: comment out tensors which occurs error on GPU

* chore: update comment and readme

* chore: update ggml to recent

* chore: add more performance test results

* chore: add more performance test results

* chore: fix problem of reading file more than 2 gb

* chore: merge master

* chore: remove unused comment

* chore: fix for comments

* Update README.md

* Update rwkv.cpp

---------

Co-authored-by: Alex <saharNooby@users.noreply.github.com>
2023-05-29 17:10:19 +05:00
..
prompt punish repetitions & break if END_OF_TEXT & decouple prompts from chat script (#37) 2023-04-30 18:50:05 +05:00
20B_tokenizer.json Add text generation and chat scripts 2023-04-02 15:03:31 +04:00
chat_with_bot.py Feature add cublas support (#65) 2023-05-29 17:10:19 +05:00
convert_pytorch_to_ggml.py Various improvements & upgrade ggml (#75) 2023-05-27 16:02:24 +05:00
convert_pytorch_to_ggml.test.py Various improvements & upgrade ggml (#75) 2023-05-27 16:02:24 +05:00
generate_completions.py Flush output every token in generate_completions.py (#73) 2023-05-26 17:23:58 +05:00
measure_pexplexity.py Sync ggml with upstream (#38) 2023-04-22 20:25:29 +05:00
merge_lora_into_ggml.py Various improvements & upgrade ggml (#75) 2023-05-27 16:02:24 +05:00
quantize.py Various improvements & upgrade ggml (#75) 2023-05-27 16:02:24 +05:00
requirements.txt Add text generation and chat scripts 2023-04-02 15:03:31 +04:00
rwkv_cpp_model.py Feature add cublas support (#65) 2023-05-29 17:10:19 +05:00
rwkv_cpp_shared_library.py Feature add cublas support (#65) 2023-05-29 17:10:19 +05:00
sampling.py Add text generation and chat scripts 2023-04-02 15:03:31 +04:00