extend bucket_internal to SAMPLE generation mode#819
Merged
Conversation
xt574chen
requested review from
bhargaveede,
ssarkar2 and
vivekgoe
as code owners
Contributor
|
Changes look good to me. Same as we have in greedy search and enables bucketing in sampling mode too. |
Contributor
Author
|
@regisss Could u help review and merge it? |
ssarkar2
approved these changes
Apr 22, 2024
regisss
approved these changes
Apr 26, 2024
ccrhx4
pushed a commit
to ccrhx4/ccrhx4.optimum-habana
that referenced
this pull request
May 11, 2024
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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
4 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
What does this PR do?
REF: HabanaAI#84
Extend function #24 to sample mode.
The command to reproduce performance is as follows:
python ../gaudi_spawn.py --use_deepspeed --world_size 4 run_generation.py --model_name_or_path meta-llama/Llama-2-70b-hf --use_hpu_graphs --use_kv_cache --max_input_tokens 128 --max_new_tokens 2048 --batch_size 240 --attn_softmax_bf16 --trim_logits --bf16 --reuse_cache --warmup 1 --n_iterations 1 --limit_hpu_graphs --do_sample --bucket_size 256 --bucket_internal