Wt/camb/interface #31
Closed
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
…nLM#2979) * Add tool role to the base chat template * fix UT
* support w8a8 smooth_quant and loading * optimize int8 * fix fp8 kernels * update docs for w8a8 * resolve comments * resolve comments * fix ut * disable not quant last norm * disable quant last norm for cogvlm and minicpmv26 models --------- Co-authored-by: grimoire <[email protected]>
* first * better tuning * restore tuning value
* remove threadsafe * optimize performance * 22.4 * 22.5 * delete jsonl * add docs * fix link * rst * remove sleep req step * remove scheduler sleep * fix ut * recovery async engine
* Update ascend get_started.md * Update ascend get_started.md * fix Dockerfile_aarch64_ascend
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Motivation
This PR changes llm op interface of paged_prefiil_attention.
Modification
Add relevant params to dlinfer attention backend and kernel
Added params requested by tmo:
cu_seq_lens_kv (Tensor): The cumulative sequence lengths of the key/value sequences.
max_kv_seq_len (int): The maximum length of any key/value sequence.