Sang Park
Sang Park
HTML tags should be removed from the GitHub's anchor tag. See below: ``` - [Heading test withHTML tags](#heading-test-withhtml-tags) ... # Heading test withHTML tags ```
- Fix benchmark bug that `bench_naive` falls into an infinite loop when pattern has matched. - Print out pattern matching count. - Reduce pattern length to increase matching probability.
Add preprocess exception handling for 3 type of errors: - size of source is 0 - `chatgpt` or `bing` is not in roles. - The order of `human` and `assistant`...
In the GPT guide(https://github.com/NVIDIA/FasterTransformer/blob/main/docs/gpt_guide.md#workflow), Fig 2 shows `fuseQKV masked attention`, which looks very similar to **Flash Attention**. However, there's no longer any mention of `fuseQKV masked attention` or 'Flash Attention'...
The spelling of the term "request" has been corrected, which was previously mistakenly written as "requeset" in the error log message.