Fixing linear_activation_tensor dynamic quant #622
Merged
Conversation
This file contains 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
Summary: dynamic quant was broken for generate due to no repr function Test Plan: sh benchmarks.sh 20240806170037, tok/s= 9.54, mem/s= 63.14 GB/s, peak_mem= 8.61 GB, model_size= 6.62 GB quant: int8dq, mod: Llama-2-7b-chat-hf, kv_quant: False, compile: True, compile_prefill: False, dtype: torch.bfloat16, device: cuda repro: python generate.py --quantization int8dq --checkpoint_path ../../../checkpoints/meta-llama/Llama-2-7b-chat-hf/model.pth --device cuda --precision torch.bfloat16 --compile --num_samples 5 --max_new_tokens 200 --top_k 200 --temperature 0.8 Reviewers: Subscribers: Tasks: Tags:
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/ao/622
Note: Links to docs will display an error until the docs builds have been completed. ✅ No FailuresAs of commit b8099aa with merge base 04e5a9e ( This comment was automatically generated by Dr. CI and updates every 15 minutes. |
facebook-github-bot
added
the
CLA Signed
jerryzh168
approved these changes
Aug 7, 2024
HDCharles
added a commit
that referenced
this pull request
Aug 7, 2024
Summary: dynamic quant was broken for generate due to no repr function Test Plan: sh benchmarks.sh 20240806170037, tok/s= 9.54, mem/s= 63.14 GB/s, peak_mem= 8.61 GB, model_size= 6.62 GB quant: int8dq, mod: Llama-2-7b-chat-hf, kv_quant: False, compile: True, compile_prefill: False, dtype: torch.bfloat16, device: cuda repro: python generate.py --quantization int8dq --checkpoint_path ../../../checkpoints/meta-llama/Llama-2-7b-chat-hf/model.pth --device cuda --precision torch.bfloat16 --compile --num_samples 5 --max_new_tokens 200 --top_k 200 --temperature 0.8 Reviewers: Subscribers: Tasks: Tags:
jainapurva
pushed a commit
that referenced
this pull request
Aug 7, 2024
Summary: dynamic quant was broken for generate due to no repr function Test Plan: sh benchmarks.sh 20240806170037, tok/s= 9.54, mem/s= 63.14 GB/s, peak_mem= 8.61 GB, model_size= 6.62 GB quant: int8dq, mod: Llama-2-7b-chat-hf, kv_quant: False, compile: True, compile_prefill: False, dtype: torch.bfloat16, device: cuda repro: python generate.py --quantization int8dq --checkpoint_path ../../../checkpoints/meta-llama/Llama-2-7b-chat-hf/model.pth --device cuda --precision torch.bfloat16 --compile --num_samples 5 --max_new_tokens 200 --top_k 200 --temperature 0.8 Reviewers: Subscribers: Tasks: Tags:
yanbing-j
pushed a commit
to yanbing-j/ao
that referenced
this pull request
Dec 9, 2024
* add desktop.json * add fast * remove embedding
yanbing-j
pushed a commit
to yanbing-j/ao
that referenced
this pull request
Dec 9, 2024
* executable README * fix title of CI workflow * markup commands in markdown * extend the markup-markdown language * Automatically identify cuda from nvidia-smi in install-requirements (pytorch#606) * Automatically identify cuda from nvidia-smi in install-requirements * Update README.md --------- Co-authored-by: Michael Gschwind <61328285+mikekgfb@users.noreply.github.com> * Unbreak zero-temperature sampling (pytorch#599) Fixes pytorch#581. * Improve process README * [retake] Add sentencepiece tokenizer (pytorch#626) * Add sentencepiece tokenizer Summary: Test Plan: Reviewers: Subscribers: Tasks: Tags: * Add white space Summary: Test Plan: Reviewers: Subscribers: Tasks: Tags: * Handle white space: Summary: Test Plan: Reviewers: Subscribers: Tasks: Tags: * Handle control ids Summary: Test Plan: Reviewers: Subscribers: Tasks: Tags: * More cleanup Summary: Test Plan: Reviewers: Subscribers: Tasks: Tags: * Lint Summary: Test Plan: Reviewers: Subscribers: Tasks: Tags: * Use unique_ptr Summary: Test Plan: Reviewers: Subscribers: Tasks: Tags: * Use a larger runner Summary: Test Plan: Reviewers: Subscribers: Tasks: Tags: * Debug Summary: Test Plan: Reviewers: Subscribers: Tasks: Tags: * Debug Summary: Test Plan: Reviewers: Subscribers: Tasks: Tags: * Cleanup * Update install_utils.sh to use python3 instead of python (pytorch#636) As titled. On some devices `python` and `python3` are pointing to different environments so good to unify them. * Fix quantization doc to specify dytpe limitation on a8w4dq (pytorch#629) Summary: Test Plan: Reviewers: Subscribers: Tasks: Tags: Co-authored-by: Kimish Patel <kimishpatel@fb.com> * add desktop.json (pytorch#622) * add desktop.json * add fast * remove embedding * improvements * update readme from doc branch * tab/spc * fix errors in updown language * fix errors in updown language, and [skip]: begin/end * fix errors in updown language, and [skip]: begin/end * a storied run * stories run on readme instructions does not need HF token * increase timeout * check for hang un hf_login * executable README improvements * typo * typo --------- Co-authored-by: Ian Barber <ian.barber@gmail.com> Co-authored-by: Scott Wolchok <swolchok@meta.com> Co-authored-by: Mengwei Liu <larryliu0820@users.noreply.github.com> Co-authored-by: Kimish Patel <kimishpatel@fb.com> Co-authored-by: Scott Roy <161522778+metascroy@users.noreply.github.com>
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.
Summary: dynamic quant was broken for generate due to no repr function
Test Plan: sh benchmarks.sh
20240806170037, tok/s= 9.54, mem/s= 63.14 GB/s, peak_mem= 8.61 GB, model_size= 6.62 GB quant: int8dq, mod: Llama-2-7b-chat-hf, kv_quant: False, compile: True, compile_prefill: False, dtype: torch.bfloat16, device: cuda repro: python generate.py --quantization int8dq --checkpoint_path ../../../checkpoints/meta-llama/Llama-2-7b-chat-hf/model.pth --device cuda --precision torch.bfloat16 --compile --num_samples 5 --max_new_tokens 200 --top_k 200 --temperature 0.8
Reviewers:
Subscribers:
Tasks:
Tags: