[int8 woq] make the scale type the same as input for bf16 autocast #534
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
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/ao/534
Note: Links to docs will display an error until the docs builds have been completed. ✅ No FailuresAs of commit ea32965 with merge base 5787e9e ( This comment was automatically generated by Dr. CI and updates every 15 minutes. |
facebook-github-bot
added
the
CLA Signed
|
@jerryzh168 @jgong5 @leslie-fang-intel Please help review the PR, thanks! |
leslie-fang-intel
approved these changes
Jul 23, 2024
|
can you check the output_code diff for int8_weight_only())
|
Hi Jerry, I found no output_code diff and here is the output_code: In addition, although the output_code can be printed, I encountered an error no matter this PR was applied or not. |
jgong5
approved these changes
Jul 24, 2024
|
@HDCharles @jerryzh168 Could you help review? Thanks. |
jerryzh168
approved these changes
Jul 26, 2024
|
please make sure the test passes before landing |
Valentine233
force-pushed
the
int8_woq_scale_type
branch
from
7b92973 to
ea32965
Compare
|
the error might be the same one as #515, I'll see if I can repro as well next week |
|
Hi @jerryzh168, how could I re-trigger the CIs? |
looks like it requires approval, I just approved the CI to run |
dbyoung18
pushed a commit
to dbyoung18/ao
that referenced
this pull request
Jul 31, 2024
yanbing-j
pushed a commit
to yanbing-j/ao
that referenced
this pull request
Dec 9, 2024
yanbing-j
pushed a commit
to yanbing-j/ao
that referenced
this pull request
Dec 9, 2024
* make --device fast the default * Update iOS.md (pytorch#517) * Update iOS.md * Update iOS.md * Pip to pip3 (pytorch#504) * remove macos-12 test * pip to pip3 * break aoti CI jobs separately (pytorch#500) * init * fixes * more fixes * fixes * fix * fix * bug fix * add objcopy update * suppress int8 * undefined variable --------- Co-authored-by: Michael Gschwind <[email protected]> * Support llama3 in chat in run.cpp (pytorch#486) * refactor chat runner in preparation for llama3 * add sketch for llama3 prompt template and move to returning tokens * fix tiktoken * fixes to chat * add default llama_ver * Add tests for quantize json, add cuda device specification and precision to cuda.json (pytorch#519) * remove code for no KV Cache path (pytorch#527) * Update ADVANCED-USERS.md (pytorch#529) Update Advanced Users description to reflect changes in the repo since the description was initially created. * runner-aoti on cuda (pytorch#531) * runner-aoti on cuda * transfer results back to CPU * transfer results back to CPU * runner-aoti on cuda * Update runner_build.md (pytorch#530) Update description of runner and build process in runner_build.md * clean up runner code a little (pytorch#532) * clean up runner code a little * update * update * pull out generate loop in chat * updates * edit docs * typo * move int8 linear class and function into qops.py (pytorch#534) * add dtype tests for runner-aoti + runner-et (pytorch#539) * add dtype tests for runner-aoti + runner-et * typo * Quantized embedding (pytorch#536) * move int8 linear class and function into qops.py * move Quantized Embedding to qops.py * Move Linear int4 to qops (pytorch#537) * move int8 linear class and function into qops.py * move Quantized Embedding to qops.py * move int4 linear to qops * Revert "add dtype tests for runner-aoti + runner-et (pytorch#539)" (pytorch#548) This reverts commit a7a24577a65be67ac9ae4dc05452f35d9c49e5d1. * fix generate for llama3 (pytorch#538) * fix generate for llama3 * switch more things to C * remove C++ header * add delegation visualization instructions (pytorch#551) * Add dtype runner aoti (pytorch#552) * add dtype tests for runner-aoti + runner-et * typo * add dtype test runner-aoti * test sdpa with fp16 (pytorch#553) * test sdpa with fp16 * kv cache fp32 * typo * update (pytorch#560) * Only support newest versions of lm-eval (pytorch#556) Summary: remove support for lm-eval 0.3 to reduce the options we have Test Plan: CI Reviewers: Subscribers: Tasks: Tags: * split cpu eval CI by dtype (pytorch#554) * split cpu eval CI by dtype * fix * differentiate names with checks * keep one name the same as old * fix * Removing duplicate HF issue message from README (pytorch#559) Co-authored-by: Michael Gschwind <[email protected]> * doc updates (pytorch#567) * Add VM-safe MPS check --------- Co-authored-by: Anthony Shoumikhin <[email protected]> Co-authored-by: metascroy <[email protected]> Co-authored-by: Nikita Shulga <[email protected]> Co-authored-by: lucylq <[email protected]> Co-authored-by: Jerry Zhang <[email protected]> Co-authored-by: Jack-Khuu <[email protected]>
yanbing-j
pushed a commit
to yanbing-j/ao
that referenced
this pull request
Dec 9, 2024
* code beautification * code beautification, move functions together * make --device fast the default (pytorch#515) * make --device fast the default * Update iOS.md (pytorch#517) * Update iOS.md * Update iOS.md * Pip to pip3 (pytorch#504) * remove macos-12 test * pip to pip3 * break aoti CI jobs separately (pytorch#500) * init * fixes * more fixes * fixes * fix * fix * bug fix * add objcopy update * suppress int8 * undefined variable --------- Co-authored-by: Michael Gschwind <[email protected]> * Support llama3 in chat in run.cpp (pytorch#486) * refactor chat runner in preparation for llama3 * add sketch for llama3 prompt template and move to returning tokens * fix tiktoken * fixes to chat * add default llama_ver * Add tests for quantize json, add cuda device specification and precision to cuda.json (pytorch#519) * remove code for no KV Cache path (pytorch#527) * Update ADVANCED-USERS.md (pytorch#529) Update Advanced Users description to reflect changes in the repo since the description was initially created. * runner-aoti on cuda (pytorch#531) * runner-aoti on cuda * transfer results back to CPU * transfer results back to CPU * runner-aoti on cuda * Update runner_build.md (pytorch#530) Update description of runner and build process in runner_build.md * clean up runner code a little (pytorch#532) * clean up runner code a little * update * update * pull out generate loop in chat * updates * edit docs * typo * move int8 linear class and function into qops.py (pytorch#534) * add dtype tests for runner-aoti + runner-et (pytorch#539) * add dtype tests for runner-aoti + runner-et * typo * Quantized embedding (pytorch#536) * move int8 linear class and function into qops.py * move Quantized Embedding to qops.py * Move Linear int4 to qops (pytorch#537) * move int8 linear class and function into qops.py * move Quantized Embedding to qops.py * move int4 linear to qops * Revert "add dtype tests for runner-aoti + runner-et (pytorch#539)" (pytorch#548) This reverts commit a7a24577a65be67ac9ae4dc05452f35d9c49e5d1. * fix generate for llama3 (pytorch#538) * fix generate for llama3 * switch more things to C * remove C++ header * add delegation visualization instructions (pytorch#551) * Add dtype runner aoti (pytorch#552) * add dtype tests for runner-aoti + runner-et * typo * add dtype test runner-aoti * test sdpa with fp16 (pytorch#553) * test sdpa with fp16 * kv cache fp32 * typo * update (pytorch#560) * Only support newest versions of lm-eval (pytorch#556) Summary: remove support for lm-eval 0.3 to reduce the options we have Test Plan: CI Reviewers: Subscribers: Tasks: Tags: * split cpu eval CI by dtype (pytorch#554) * split cpu eval CI by dtype * fix * differentiate names with checks * keep one name the same as old * fix * Removing duplicate HF issue message from README (pytorch#559) Co-authored-by: Michael Gschwind <[email protected]> * doc updates (pytorch#567) * Add VM-safe MPS check --------- Co-authored-by: Anthony Shoumikhin <[email protected]> Co-authored-by: metascroy <[email protected]> Co-authored-by: Nikita Shulga <[email protected]> Co-authored-by: lucylq <[email protected]> Co-authored-by: Jerry Zhang <[email protected]> Co-authored-by: Jack-Khuu <[email protected]> * add unpacking support (pytorch#525) * add unpacking support * fix typos and linter * perform parallel prefill when possible (pytorch#568) * perform parallel prefill when possible * typo * disable hack * remove print * remove debug messages which prevent export * fixes * stream results in generate.py (pytorch#571) * remove logging interfering with export --------- Co-authored-by: Anthony Shoumikhin <[email protected]> Co-authored-by: metascroy <[email protected]> Co-authored-by: Nikita Shulga <[email protected]> Co-authored-by: lucylq <[email protected]> Co-authored-by: Jerry Zhang <[email protected]> Co-authored-by: Jack-Khuu <[email protected]>
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.
Under bf16 autocast, input's type would convert from fp32 to bf16 because of torch.mm. However, scale's type is still fp32, so as the final output. To fix the issue, we make scale's type the same as the output of torch.mm, to get a bf16 scale.
FX graph before:
FX graph after: