quantization: make x86 as default backend (part 1) #88799
Conversation
[ghstack-poisoned]
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/88799
Note: Links to docs will display an error until the docs builds have been completed. ✅ No FailuresAs of commit 4c6c326: This comment was automatically generated by Dr. CI and updates every 15 minutes. |
github-actions
bot
added
the
oncall: quantization
| if (fbgemm::fbgemmSupportedCPU()) { | ||
| // The X86 qengine is available if and only if FBGEMM is available | ||
| engines.push_back(at::kX86); | ||
| // The X86 qengine is available if and only if FBGEMM is available | ||
| engines.push_back(at::kFBGEMM); |
There was a problem hiding this comment.
The order is not important now?
There was a problem hiding this comment.
maybe, I just revert @jerryzh168 's PR changes.
There was a problem hiding this comment.
the order is still important, whatever comes the last is the default, and we want to fix it in a separate PR
XiaobingSuper
added
the
intel priority
|
@XiaobingSuper feel free to merge when ready |
cc jerryzh168 jianyuh raghuramank100 jamesr66a vkuzo jgong5 Xia-Weiwen leslie-fang-intel [ghstack-poisoned]
cc jerryzh168 jianyuh raghuramank100 jamesr66a vkuzo jgong5 Xia-Weiwen leslie-fang-intel [ghstack-poisoned]
cc jerryzh168 jianyuh raghuramank100 jamesr66a vkuzo jgong5 Xia-Weiwen leslie-fang-intel [ghstack-poisoned]
|
@pytorchbot merge |
Merge startedYour change will be merged once all checks pass (ETA 0-4 Hours). Learn more about merging in the wiki. Questions? Feedback? Please reach out to the PyTorch DevX Team |
| #ifdef USE_FBGEMM | ||
| if (fbgemm::fbgemmSupportedCPU()) { | ||
| // The X86 qengine is available if and only if FBGEMM is available | ||
| engines.push_back(at::kX86); |
There was a problem hiding this comment.
actually this PR is not making x86 the default quantized engine yet, I believe with the current code you'll need to switch the order, but I have #89804, and maybe you can change the default more explicitly after my PR is landed
There was a problem hiding this comment.
Since this PR was already landed, I changed the PR title to avoid misunderstanding. @XiaobingSuper Could you please follow up the changes after #89804 is landed? Thanks!
jgong5
changed the title
Pull Request resolved: pytorch#88799 Approved by: https://github.com/kit1980
Stack from ghstack (oldest at bottom):
cc @jerryzh168 @jianyuh @raghuramank100 @jamesr66a @vkuzo @jgong5 @Xia-Weiwen @leslie-fang-intel