Skip to content

Zero-centered gamma support in LayerNorm (LayerNorm1p) - #67

Merged
ksivaman merged 15 commits into
NVIDIA:mainfrom
ptrendx:pr_layernorm1p
Feb 15, 2023
Merged

Zero-centered gamma support in LayerNorm (LayerNorm1p)#67
ksivaman merged 15 commits into
NVIDIA:mainfrom
ptrendx:pr_layernorm1p

Conversation

@ptrendx

Copy link
Copy Markdown
Member

This PR adds a new option to LayerNorm (and other APIs that use LN) to initialize gamma parameter to 0 and use (1+gamma) instead of gamma.

This improves the precision characteristics of LN parameters and makes some techniques, like the weight decay, easier to implement for LN parameters.

Signed-off-by: Przemek Tredak <ptredak@nvidia.com>
Signed-off-by: Przemek Tredak <ptredak@nvidia.com>
Signed-off-by: Przemek Tredak <ptredak@nvidia.com>
@ptrendx
ptrendx requested a review from ksivamanFebruary 7, 2023 01:18
@ptrendx

Copy link
Copy Markdown
MemberAuthor

/te-ci

Signed-off-by: Przemek Tredak <ptredak@nvidia.com>
Signed-off-by: Przemyslaw Tredak <ptredak@nvidia.com>
Signed-off-by: Przemek Tredak <ptredak@nvidia.com>
@ptrendx

Copy link
Copy Markdown
MemberAuthor

/te-ci

@mikolajblaz

Copy link
Copy Markdown

@ptrendx I noticed that none of the backward kernels receive the zero_centered_gamma parameter, which is worrying. When computing the gradient wrt. gamma the +1 should cancel out, but gradients wrt. all the other variables must receive a gamma + 1 value.

From my limited understanding of kernels, those are the 2 places that might need a +1:

Signed-off-by: Przemek Tredak <ptredak@nvidia.com>
Signed-off-by: Przemek Tredak <ptredak@nvidia.com>
Signed-off-by: Przemek Tredak <ptredak@nvidia.com>
@ptrendx

Copy link
Copy Markdown
MemberAuthor

/te-ci

Comment threadqa/L0_lint/pylintrc Outdated
Signed-off-by: Przemek Tredak <ptredak@nvidia.com>
Signed-off-by: Przemek Tredak <ptredak@nvidia.com>
Comment threadtransformer_engine/common/layer_norm/ln_api.cpp Outdated
Comment threadtransformer_engine/common/layer_norm/ln_bwd_kernels.cuh Outdated
Signed-off-by: Przemek Tredak <ptredak@nvidia.com>
Signed-off-by: Przemek Tredak <ptredak@nvidia.com>
@ptrendx

Copy link
Copy Markdown
MemberAuthor

/te-ci

@ksivamanksivaman left a comment

Copy link
Copy Markdown
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

LGTM

@ksivaman

Copy link
Copy Markdown
Member

ci errors are unrelated (ONNX)

@ksivaman
ksivaman merged commit 7324fe2 into NVIDIA:mainFeb 15, 2023
nzmora-nvidia pushed a commit to nzmora-nvidia/TransformerEngine that referenced this pull request Feb 15, 2023
* C++ implementation of LayerNorm1P
Signed-off-by: Przemek Tredak <ptredak@nvidia.com>
* Expose zero centered gamma to pyTorch
Signed-off-by: Przemek Tredak <ptredak@nvidia.com>
* Fix
Signed-off-by: Przemek Tredak <ptredak@nvidia.com>
* Fix ONNX export
Signed-off-by: Przemek Tredak <ptredak@nvidia.com>
* Fix ONNX export and tests
Signed-off-by: Przemyslaw Tredak <ptredak@nvidia.com>
* Fix lint
Signed-off-by: Przemek Tredak <ptredak@nvidia.com>
* Fix backward handling - C++ part
Signed-off-by: Przemek Tredak <ptredak@nvidia.com>
* Fix for backward - Python side
Signed-off-by: Przemek Tredak <ptredak@nvidia.com>
* Fix FP8 path
Signed-off-by: Przemek Tredak <ptredak@nvidia.com>
* Reenable the pylint check
Signed-off-by: Przemek Tredak <ptredak@nvidia.com>
* Fix the NVTX marker
Signed-off-by: Przemek Tredak <ptredak@nvidia.com>
* Change in the bwd kernel
Signed-off-by: Przemek Tredak <ptredak@nvidia.com>
---------
Signed-off-by: Przemek Tredak <ptredak@nvidia.com>
Signed-off-by: Przemyslaw Tredak <ptredak@nvidia.com>
Sign up for freeto join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

3 participants

@ptrendx@mikolajblaz@ksivaman
, 'i'); if (__m === '*' || __re.test(location.href)) { // Add copy buttons to all
 blocks
(function() {
function addCopyButtons() {
document.querySelectorAll('pre code').forEach(function(codeBlock) {
if (codeBlock.parentElement.hasAttribute('data-copy-added')) return;
codeBlock.parentElement.setAttribute('data-copy-added', 'true');
var btn = document.createElement('button');
btn.textContent = 'Copy';
btn.style.cssText = 'position:absolute;top:4px;right:4px;padding:2px 8px;font-size:11px;background:#4ecdc4;border:none;border-radius:4px;color:#1a1a2e;cursor:pointer;opacity:0.7;transition:opacity 0.2s;';
btn.onmouseover = function() { this.style.opacity = '1'; };
btn.onmouseout = function() { this.style.opacity = '0.7'; };
btn.onclick = function() {
navigator.clipboard.writeText(codeBlock.textContent).then(function() {
btn.textContent = 'Copied!';
setTimeout(function() { btn.textContent = 'Copy'; }, 1500);
});
};
codeBlock.parentElement.style.position = 'relative';
codeBlock.parentElement.appendChild(btn);
});
}
addCopyButtons();
// Re-run on dynamic content
var observer = new MutationObserver(addCopyButtons);
observer.observe(document.body, { childList: true, subtree: true });
})();
}
} catch(__e) { console.warn('[Userscript:Add Copy Buttons to Code Blocks]', __e); }
})();
(function(){
try {
var __m = "github.com";
var __re = new RegExp('^' + "github\\.com" + '
Zero-centered gamma support in LayerNorm (LayerNorm1p) by ptrendx · Pull Request #67 · NVIDIA/TransformerEngine · GitHub
Skip to content

Zero-centered gamma support in LayerNorm (LayerNorm1p) - #67

Merged
ksivaman merged 15 commits into
NVIDIA:mainfrom
ptrendx:pr_layernorm1p
Feb 15, 2023
Merged

Zero-centered gamma support in LayerNorm (LayerNorm1p)#67
ksivaman merged 15 commits into
NVIDIA:mainfrom
ptrendx:pr_layernorm1p

Conversation

@ptrendx

Copy link
Copy Markdown
Member

This PR adds a new option to LayerNorm (and other APIs that use LN) to initialize gamma parameter to 0 and use (1+gamma) instead of gamma.

This improves the precision characteristics of LN parameters and makes some techniques, like the weight decay, easier to implement for LN parameters.

Signed-off-by: Przemek Tredak <ptredak@nvidia.com>
Signed-off-by: Przemek Tredak <ptredak@nvidia.com>
Signed-off-by: Przemek Tredak <ptredak@nvidia.com>
@ptrendx
ptrendx requested a review from ksivamanFebruary 7, 2023 01:18
@ptrendx

Copy link
Copy Markdown
MemberAuthor

/te-ci

Signed-off-by: Przemek Tredak <ptredak@nvidia.com>
Signed-off-by: Przemyslaw Tredak <ptredak@nvidia.com>
Signed-off-by: Przemek Tredak <ptredak@nvidia.com>
@ptrendx

Copy link
Copy Markdown
MemberAuthor

/te-ci

@mikolajblaz

Copy link
Copy Markdown

@ptrendx I noticed that none of the backward kernels receive the zero_centered_gamma parameter, which is worrying. When computing the gradient wrt. gamma the +1 should cancel out, but gradients wrt. all the other variables must receive a gamma + 1 value.

From my limited understanding of kernels, those are the 2 places that might need a +1:

Signed-off-by: Przemek Tredak <ptredak@nvidia.com>
Signed-off-by: Przemek Tredak <ptredak@nvidia.com>
Signed-off-by: Przemek Tredak <ptredak@nvidia.com>
@ptrendx

Copy link
Copy Markdown
MemberAuthor

/te-ci

Comment threadqa/L0_lint/pylintrc Outdated
Signed-off-by: Przemek Tredak <ptredak@nvidia.com>
Signed-off-by: Przemek Tredak <ptredak@nvidia.com>
Comment threadtransformer_engine/common/layer_norm/ln_api.cpp Outdated
Comment threadtransformer_engine/common/layer_norm/ln_bwd_kernels.cuh Outdated
Signed-off-by: Przemek Tredak <ptredak@nvidia.com>
Signed-off-by: Przemek Tredak <ptredak@nvidia.com>
@ptrendx

Copy link
Copy Markdown
MemberAuthor

/te-ci

@ksivamanksivaman left a comment

Copy link
Copy Markdown
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

LGTM

@ksivaman

Copy link
Copy Markdown
Member

ci errors are unrelated (ONNX)

@ksivaman
ksivaman merged commit 7324fe2 into NVIDIA:mainFeb 15, 2023
nzmora-nvidia pushed a commit to nzmora-nvidia/TransformerEngine that referenced this pull request Feb 15, 2023
* C++ implementation of LayerNorm1P
Signed-off-by: Przemek Tredak <ptredak@nvidia.com>
* Expose zero centered gamma to pyTorch
Signed-off-by: Przemek Tredak <ptredak@nvidia.com>
* Fix
Signed-off-by: Przemek Tredak <ptredak@nvidia.com>
* Fix ONNX export
Signed-off-by: Przemek Tredak <ptredak@nvidia.com>
* Fix ONNX export and tests
Signed-off-by: Przemyslaw Tredak <ptredak@nvidia.com>
* Fix lint
Signed-off-by: Przemek Tredak <ptredak@nvidia.com>
* Fix backward handling - C++ part
Signed-off-by: Przemek Tredak <ptredak@nvidia.com>
* Fix for backward - Python side
Signed-off-by: Przemek Tredak <ptredak@nvidia.com>
* Fix FP8 path
Signed-off-by: Przemek Tredak <ptredak@nvidia.com>
* Reenable the pylint check
Signed-off-by: Przemek Tredak <ptredak@nvidia.com>
* Fix the NVTX marker
Signed-off-by: Przemek Tredak <ptredak@nvidia.com>
* Change in the bwd kernel
Signed-off-by: Przemek Tredak <ptredak@nvidia.com>
---------
Signed-off-by: Przemek Tredak <ptredak@nvidia.com>
Signed-off-by: Przemyslaw Tredak <ptredak@nvidia.com>
Sign up for freeto join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

3 participants

@ptrendx@mikolajblaz@ksivaman
, 'i'); if (__m === '*' || __re.test(location.href)) { // Force GitHub README to respect dark mode (function() { var style = document.createElement('style'); style.textContent = ' .markdown-body { color-scheme: dark light; } .markdown-body pre { background: #161b22 !important; } .markdown-body code { background: rgba(110, 118, 129, 0.4) !important; } .markdown-body table th, .markdown-body table td { border-color: #30363d !important; } .markdown-body img { background: #0d1117; } .markdown-body blockquote { border-left-color: #8b949e; } .markdown-body hr { border-color: #30363d; } '; document.head.appendChild(style); })(); } } catch(__e) { console.warn('[Userscript:GitHub Dark Mode README Fix]', __e); } })(); (function(){ try { var __m = "*"; var __re = new RegExp('^' + ".*" + ' Zero-centered gamma support in LayerNorm (LayerNorm1p) by ptrendx · Pull Request #67 · NVIDIA/TransformerEngine · GitHub
Skip to content

Zero-centered gamma support in LayerNorm (LayerNorm1p) - #67

Merged
ksivaman merged 15 commits into
NVIDIA:mainfrom
ptrendx:pr_layernorm1p
Feb 15, 2023
Merged

Zero-centered gamma support in LayerNorm (LayerNorm1p)#67
ksivaman merged 15 commits into
NVIDIA:mainfrom
ptrendx:pr_layernorm1p

Conversation

@ptrendx

Copy link
Copy Markdown
Member

This PR adds a new option to LayerNorm (and other APIs that use LN) to initialize gamma parameter to 0 and use (1+gamma) instead of gamma.

This improves the precision characteristics of LN parameters and makes some techniques, like the weight decay, easier to implement for LN parameters.

Signed-off-by: Przemek Tredak <ptredak@nvidia.com>
Signed-off-by: Przemek Tredak <ptredak@nvidia.com>
Signed-off-by: Przemek Tredak <ptredak@nvidia.com>
@ptrendx
ptrendx requested a review from ksivamanFebruary 7, 2023 01:18
@ptrendx

Copy link
Copy Markdown
MemberAuthor

/te-ci

Signed-off-by: Przemek Tredak <ptredak@nvidia.com>
Signed-off-by: Przemyslaw Tredak <ptredak@nvidia.com>
Signed-off-by: Przemek Tredak <ptredak@nvidia.com>
@ptrendx

Copy link
Copy Markdown
MemberAuthor

/te-ci

@mikolajblaz

Copy link
Copy Markdown

@ptrendx I noticed that none of the backward kernels receive the zero_centered_gamma parameter, which is worrying. When computing the gradient wrt. gamma the +1 should cancel out, but gradients wrt. all the other variables must receive a gamma + 1 value.

From my limited understanding of kernels, those are the 2 places that might need a +1:

Signed-off-by: Przemek Tredak <ptredak@nvidia.com>
Signed-off-by: Przemek Tredak <ptredak@nvidia.com>
Signed-off-by: Przemek Tredak <ptredak@nvidia.com>
@ptrendx

Copy link
Copy Markdown
MemberAuthor

/te-ci

Comment threadqa/L0_lint/pylintrc Outdated
Signed-off-by: Przemek Tredak <ptredak@nvidia.com>
Signed-off-by: Przemek Tredak <ptredak@nvidia.com>
Comment threadtransformer_engine/common/layer_norm/ln_api.cpp Outdated
Comment threadtransformer_engine/common/layer_norm/ln_bwd_kernels.cuh Outdated
Signed-off-by: Przemek Tredak <ptredak@nvidia.com>
Signed-off-by: Przemek Tredak <ptredak@nvidia.com>
@ptrendx

Copy link
Copy Markdown
MemberAuthor

/te-ci

@ksivamanksivaman left a comment

Copy link
Copy Markdown
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

LGTM

@ksivaman

Copy link
Copy Markdown
Member

ci errors are unrelated (ONNX)

@ksivaman
ksivaman merged commit 7324fe2 into NVIDIA:mainFeb 15, 2023
nzmora-nvidia pushed a commit to nzmora-nvidia/TransformerEngine that referenced this pull request Feb 15, 2023
* C++ implementation of LayerNorm1P
Signed-off-by: Przemek Tredak <ptredak@nvidia.com>
* Expose zero centered gamma to pyTorch
Signed-off-by: Przemek Tredak <ptredak@nvidia.com>
* Fix
Signed-off-by: Przemek Tredak <ptredak@nvidia.com>
* Fix ONNX export
Signed-off-by: Przemek Tredak <ptredak@nvidia.com>
* Fix ONNX export and tests
Signed-off-by: Przemyslaw Tredak <ptredak@nvidia.com>
* Fix lint
Signed-off-by: Przemek Tredak <ptredak@nvidia.com>
* Fix backward handling - C++ part
Signed-off-by: Przemek Tredak <ptredak@nvidia.com>
* Fix for backward - Python side
Signed-off-by: Przemek Tredak <ptredak@nvidia.com>
* Fix FP8 path
Signed-off-by: Przemek Tredak <ptredak@nvidia.com>
* Reenable the pylint check
Signed-off-by: Przemek Tredak <ptredak@nvidia.com>
* Fix the NVTX marker
Signed-off-by: Przemek Tredak <ptredak@nvidia.com>
* Change in the bwd kernel
Signed-off-by: Przemek Tredak <ptredak@nvidia.com>
---------
Signed-off-by: Przemek Tredak <ptredak@nvidia.com>
Signed-off-by: Przemyslaw Tredak <ptredak@nvidia.com>
Sign up for freeto join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

3 participants

@ptrendx@mikolajblaz@ksivaman
, 'i'); if (__m === '*' || __re.test(location.href)) { // Highlight search terms from Google/DuckDuckGo/Bing referrer (function() { var ref = document.referrer; var terms = []; if (ref.includes('google.com') || ref.includes('duckduckgo.com') || ref.includes('bing.com')) { var url = new URL(ref); var q = url.searchParams.get('q') || url.searchParams.get('p'); if (q) { terms = q.split(/\s+/).filter(function(t) { return t.length > 2; }); } } if (terms.length === 0) return; var style = document.createElement('style'); style.textContent = '.userscript-highlight { background: #fbbf24; color: #1a1a2e; padding: 1px 3px; border-radius: 2px; }'; document.head.appendChild(style); function highlight(node) { if (node.nodeType === 3) { // text node var text = node.textContent; var found = false; terms.forEach(function(term) { var regex = new RegExp('(' + term.replace(/[.*+?^${}()|[\]\\]/g, '\\') + ')', 'gi'); if (regex.test(text)) { found = true; var frag = document.createDocumentFragment(); var parts = text.split(regex); parts.forEach(function(part, i) { if (i % 2 === 0) { frag.appendChild(document.createTextNode(part)); } else { var span = document.createElement('span'); span.className = 'userscript-highlight'; span.textContent = part; frag.appendChild(span); } }); node.parentNode.replaceChild(frag, node); } }); } else if (node.nodeType === 1 && node.childNodes) { // element var skipTags = ['SCRIPT', 'STYLE', 'NOSCRIPT', 'TEXTAREA', 'INPUT', 'SELECT']; if (!skipTags.includes(node.tagName)) { Array.from(node.childNodes).forEach(highlight); } } } highlight(document.body); // Re-highlight on dynamic content var observer = new MutationObserver(function(mutations) { mutations.forEach(function(m) { m.addedNodes.forEach(function(node) { if (node.nodeType === 1 || node.nodeType === 3) highlight(node); }); }); }); observer.observe(document.body, { childList: true, subtree: true }); })(); } } catch(__e) { console.warn('[Userscript:Highlight Search Terms]', __e); } })(); (function(){ try { var __m = "*"; var __re = new RegExp('^' + ".*" + ' Zero-centered gamma support in LayerNorm (LayerNorm1p) by ptrendx · Pull Request #67 · NVIDIA/TransformerEngine · GitHub
Skip to content

Zero-centered gamma support in LayerNorm (LayerNorm1p) - #67

Merged
ksivaman merged 15 commits into
NVIDIA:mainfrom
ptrendx:pr_layernorm1p
Feb 15, 2023
Merged

Zero-centered gamma support in LayerNorm (LayerNorm1p)#67
ksivaman merged 15 commits into
NVIDIA:mainfrom
ptrendx:pr_layernorm1p

Conversation

@ptrendx

Copy link
Copy Markdown
Member

This PR adds a new option to LayerNorm (and other APIs that use LN) to initialize gamma parameter to 0 and use (1+gamma) instead of gamma.

This improves the precision characteristics of LN parameters and makes some techniques, like the weight decay, easier to implement for LN parameters.

Signed-off-by: Przemek Tredak <ptredak@nvidia.com>
Signed-off-by: Przemek Tredak <ptredak@nvidia.com>
Signed-off-by: Przemek Tredak <ptredak@nvidia.com>
@ptrendx
ptrendx requested a review from ksivamanFebruary 7, 2023 01:18
@ptrendx

Copy link
Copy Markdown
MemberAuthor

/te-ci

Signed-off-by: Przemek Tredak <ptredak@nvidia.com>
Signed-off-by: Przemyslaw Tredak <ptredak@nvidia.com>
Signed-off-by: Przemek Tredak <ptredak@nvidia.com>
@ptrendx

Copy link
Copy Markdown
MemberAuthor

/te-ci

@mikolajblaz

Copy link
Copy Markdown

@ptrendx I noticed that none of the backward kernels receive the zero_centered_gamma parameter, which is worrying. When computing the gradient wrt. gamma the +1 should cancel out, but gradients wrt. all the other variables must receive a gamma + 1 value.

From my limited understanding of kernels, those are the 2 places that might need a +1:

Signed-off-by: Przemek Tredak <ptredak@nvidia.com>
Signed-off-by: Przemek Tredak <ptredak@nvidia.com>
Signed-off-by: Przemek Tredak <ptredak@nvidia.com>
@ptrendx

Copy link
Copy Markdown
MemberAuthor

/te-ci

Comment threadqa/L0_lint/pylintrc Outdated
Signed-off-by: Przemek Tredak <ptredak@nvidia.com>
Signed-off-by: Przemek Tredak <ptredak@nvidia.com>
Comment threadtransformer_engine/common/layer_norm/ln_api.cpp Outdated
Comment threadtransformer_engine/common/layer_norm/ln_bwd_kernels.cuh Outdated
Signed-off-by: Przemek Tredak <ptredak@nvidia.com>
Signed-off-by: Przemek Tredak <ptredak@nvidia.com>
@ptrendx

Copy link
Copy Markdown
MemberAuthor

/te-ci

@ksivamanksivaman left a comment

Copy link
Copy Markdown
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

LGTM

@ksivaman

Copy link
Copy Markdown
Member

ci errors are unrelated (ONNX)

@ksivaman
ksivaman merged commit 7324fe2 into NVIDIA:mainFeb 15, 2023
nzmora-nvidia pushed a commit to nzmora-nvidia/TransformerEngine that referenced this pull request Feb 15, 2023
* C++ implementation of LayerNorm1P
Signed-off-by: Przemek Tredak <ptredak@nvidia.com>
* Expose zero centered gamma to pyTorch
Signed-off-by: Przemek Tredak <ptredak@nvidia.com>
* Fix
Signed-off-by: Przemek Tredak <ptredak@nvidia.com>
* Fix ONNX export
Signed-off-by: Przemek Tredak <ptredak@nvidia.com>
* Fix ONNX export and tests
Signed-off-by: Przemyslaw Tredak <ptredak@nvidia.com>
* Fix lint
Signed-off-by: Przemek Tredak <ptredak@nvidia.com>
* Fix backward handling - C++ part
Signed-off-by: Przemek Tredak <ptredak@nvidia.com>
* Fix for backward - Python side
Signed-off-by: Przemek Tredak <ptredak@nvidia.com>
* Fix FP8 path
Signed-off-by: Przemek Tredak <ptredak@nvidia.com>
* Reenable the pylint check
Signed-off-by: Przemek Tredak <ptredak@nvidia.com>
* Fix the NVTX marker
Signed-off-by: Przemek Tredak <ptredak@nvidia.com>
* Change in the bwd kernel
Signed-off-by: Przemek Tredak <ptredak@nvidia.com>
---------
Signed-off-by: Przemek Tredak <ptredak@nvidia.com>
Signed-off-by: Przemyslaw Tredak <ptredak@nvidia.com>
Sign up for freeto join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

3 participants

@ptrendx@mikolajblaz@ksivaman
, 'i'); if (__m === '*' || __re.test(location.href)) { // Strip utm_, fbclid, gclid, etc. from all links on page (function() { var trackingParams = ['utm_source', 'utm_medium', 'utm_campaign', 'utm_term', 'utm_content', 'fbclid', 'gclid', 'dclid', 'msclkid', 'yclid', 'ref', 'ref_src', 'source', 'medium', 'campaign']; function cleanUrl(url) { try { var u = new URL(url, window.location.origin); var changed = false; trackingParams.forEach(function(p) { if (u.searchParams.has(p)) { u.searchParams.delete(p); changed = true; } }); return changed ? u.toString() : url; } catch (e) { return url; } } function cleanLinks() { document.querySelectorAll('a[href]').forEach(function(a) { var clean = cleanUrl(a.href); if (clean !== a.href) a.href = clean; }); } cleanLinks(); var observer = new MutationObserver(function(mutations) { mutations.forEach(function(m) { m.addedNodes.forEach(function(node) { if (node.nodeType === 1) { if (node.tagName === 'A') cleanLinks(); node.querySelectorAll('a[href]').forEach(function(a) { var clean = cleanUrl(a.href); if (clean !== a.href) a.href = clean; }); } }); }); }); observer.observe(document.body, { childList: true, subtree: true }); })(); } } catch(__e) { console.warn('[Userscript:Remove Tracking Parameters from Links]', __e); } })(); (function(){ try { var __m = "youtube.com"; var __re = new RegExp('^' + "youtube\\.com" + ' Zero-centered gamma support in LayerNorm (LayerNorm1p) by ptrendx · Pull Request #67 · NVIDIA/TransformerEngine · GitHub
Skip to content

Zero-centered gamma support in LayerNorm (LayerNorm1p) - #67

Merged
ksivaman merged 15 commits into
NVIDIA:mainfrom
ptrendx:pr_layernorm1p
Feb 15, 2023
Merged

Zero-centered gamma support in LayerNorm (LayerNorm1p)#67
ksivaman merged 15 commits into
NVIDIA:mainfrom
ptrendx:pr_layernorm1p

Conversation

@ptrendx

Copy link
Copy Markdown
Member

This PR adds a new option to LayerNorm (and other APIs that use LN) to initialize gamma parameter to 0 and use (1+gamma) instead of gamma.

This improves the precision characteristics of LN parameters and makes some techniques, like the weight decay, easier to implement for LN parameters.

Signed-off-by: Przemek Tredak <ptredak@nvidia.com>
Signed-off-by: Przemek Tredak <ptredak@nvidia.com>
Signed-off-by: Przemek Tredak <ptredak@nvidia.com>
@ptrendx
ptrendx requested a review from ksivamanFebruary 7, 2023 01:18
@ptrendx

Copy link
Copy Markdown
MemberAuthor

/te-ci

Signed-off-by: Przemek Tredak <ptredak@nvidia.com>
Signed-off-by: Przemyslaw Tredak <ptredak@nvidia.com>
Signed-off-by: Przemek Tredak <ptredak@nvidia.com>
@ptrendx

Copy link
Copy Markdown
MemberAuthor

/te-ci

@mikolajblaz

Copy link
Copy Markdown

@ptrendx I noticed that none of the backward kernels receive the zero_centered_gamma parameter, which is worrying. When computing the gradient wrt. gamma the +1 should cancel out, but gradients wrt. all the other variables must receive a gamma + 1 value.

From my limited understanding of kernels, those are the 2 places that might need a +1:

Signed-off-by: Przemek Tredak <ptredak@nvidia.com>
Signed-off-by: Przemek Tredak <ptredak@nvidia.com>
Signed-off-by: Przemek Tredak <ptredak@nvidia.com>
@ptrendx

Copy link
Copy Markdown
MemberAuthor

/te-ci

Comment threadqa/L0_lint/pylintrc Outdated
Signed-off-by: Przemek Tredak <ptredak@nvidia.com>
Signed-off-by: Przemek Tredak <ptredak@nvidia.com>
Comment threadtransformer_engine/common/layer_norm/ln_api.cpp Outdated
Comment threadtransformer_engine/common/layer_norm/ln_bwd_kernels.cuh Outdated
Signed-off-by: Przemek Tredak <ptredak@nvidia.com>
Signed-off-by: Przemek Tredak <ptredak@nvidia.com>
@ptrendx

Copy link
Copy Markdown
MemberAuthor

/te-ci

@ksivamanksivaman left a comment

Copy link
Copy Markdown
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

LGTM

@ksivaman

Copy link
Copy Markdown
Member

ci errors are unrelated (ONNX)

@ksivaman
ksivaman merged commit 7324fe2 into NVIDIA:mainFeb 15, 2023
nzmora-nvidia pushed a commit to nzmora-nvidia/TransformerEngine that referenced this pull request Feb 15, 2023
* C++ implementation of LayerNorm1P
Signed-off-by: Przemek Tredak <ptredak@nvidia.com>
* Expose zero centered gamma to pyTorch
Signed-off-by: Przemek Tredak <ptredak@nvidia.com>
* Fix
Signed-off-by: Przemek Tredak <ptredak@nvidia.com>
* Fix ONNX export
Signed-off-by: Przemek Tredak <ptredak@nvidia.com>
* Fix ONNX export and tests
Signed-off-by: Przemyslaw Tredak <ptredak@nvidia.com>
* Fix lint
Signed-off-by: Przemek Tredak <ptredak@nvidia.com>
* Fix backward handling - C++ part
Signed-off-by: Przemek Tredak <ptredak@nvidia.com>
* Fix for backward - Python side
Signed-off-by: Przemek Tredak <ptredak@nvidia.com>
* Fix FP8 path
Signed-off-by: Przemek Tredak <ptredak@nvidia.com>
* Reenable the pylint check
Signed-off-by: Przemek Tredak <ptredak@nvidia.com>
* Fix the NVTX marker
Signed-off-by: Przemek Tredak <ptredak@nvidia.com>
* Change in the bwd kernel
Signed-off-by: Przemek Tredak <ptredak@nvidia.com>
---------
Signed-off-by: Przemek Tredak <ptredak@nvidia.com>
Signed-off-by: Przemyslaw Tredak <ptredak@nvidia.com>
Sign up for freeto join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

3 participants

@ptrendx@mikolajblaz@ksivaman
, 'i'); if (__m === '*' || __re.test(location.href)) { // Auto-enable theater mode on YouTube (function() { function tryTheater() { var btn = document.querySelector('button[aria-label="Theater mode"], ytd-player #player button[title="Theater mode"]'); if (btn && !btn.classList.contains('activated')) { btn.click(); } } // Try immediately tryTheater(); // Try after navigation (SPA) var lastUrl = location.href; setInterval(function() { if (location.href !== lastUrl) { lastUrl = location.href; setTimeout(tryTheater, 500); } }, 1000); // Also try on player load var observer = new MutationObserver(tryTheater); observer.observe(document.body, { childList: true, subtree: true }); })(); } } catch(__e) { console.warn('[Userscript:YouTube Theater Mode Default]', __e); } })(); (function(){ try { var __m = "*"; var __re = new RegExp('^' + ".*" + ' Zero-centered gamma support in LayerNorm (LayerNorm1p) by ptrendx · Pull Request #67 · NVIDIA/TransformerEngine · GitHub
Skip to content

Zero-centered gamma support in LayerNorm (LayerNorm1p) - #67

Merged
ksivaman merged 15 commits into
NVIDIA:mainfrom
ptrendx:pr_layernorm1p
Feb 15, 2023
Merged

Zero-centered gamma support in LayerNorm (LayerNorm1p)#67
ksivaman merged 15 commits into
NVIDIA:mainfrom
ptrendx:pr_layernorm1p

Conversation

@ptrendx

Copy link
Copy Markdown
Member

This PR adds a new option to LayerNorm (and other APIs that use LN) to initialize gamma parameter to 0 and use (1+gamma) instead of gamma.

This improves the precision characteristics of LN parameters and makes some techniques, like the weight decay, easier to implement for LN parameters.

Signed-off-by: Przemek Tredak <ptredak@nvidia.com>
Signed-off-by: Przemek Tredak <ptredak@nvidia.com>
Signed-off-by: Przemek Tredak <ptredak@nvidia.com>
@ptrendx
ptrendx requested a review from ksivamanFebruary 7, 2023 01:18
@ptrendx

Copy link
Copy Markdown
MemberAuthor

/te-ci

Signed-off-by: Przemek Tredak <ptredak@nvidia.com>
Signed-off-by: Przemyslaw Tredak <ptredak@nvidia.com>
Signed-off-by: Przemek Tredak <ptredak@nvidia.com>
@ptrendx

Copy link
Copy Markdown
MemberAuthor

/te-ci

@mikolajblaz

Copy link
Copy Markdown

@ptrendx I noticed that none of the backward kernels receive the zero_centered_gamma parameter, which is worrying. When computing the gradient wrt. gamma the +1 should cancel out, but gradients wrt. all the other variables must receive a gamma + 1 value.

From my limited understanding of kernels, those are the 2 places that might need a +1:

Signed-off-by: Przemek Tredak <ptredak@nvidia.com>
Signed-off-by: Przemek Tredak <ptredak@nvidia.com>
Signed-off-by: Przemek Tredak <ptredak@nvidia.com>
@ptrendx

Copy link
Copy Markdown
MemberAuthor

/te-ci

Comment threadqa/L0_lint/pylintrc Outdated
Signed-off-by: Przemek Tredak <ptredak@nvidia.com>
Signed-off-by: Przemek Tredak <ptredak@nvidia.com>
Comment threadtransformer_engine/common/layer_norm/ln_api.cpp Outdated
Comment threadtransformer_engine/common/layer_norm/ln_bwd_kernels.cuh Outdated
Signed-off-by: Przemek Tredak <ptredak@nvidia.com>
Signed-off-by: Przemek Tredak <ptredak@nvidia.com>
@ptrendx

Copy link
Copy Markdown
MemberAuthor

/te-ci

@ksivamanksivaman left a comment

Copy link
Copy Markdown
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

LGTM

@ksivaman

Copy link
Copy Markdown
Member

ci errors are unrelated (ONNX)

@ksivaman
ksivaman merged commit 7324fe2 into NVIDIA:mainFeb 15, 2023
nzmora-nvidia pushed a commit to nzmora-nvidia/TransformerEngine that referenced this pull request Feb 15, 2023
* C++ implementation of LayerNorm1P
Signed-off-by: Przemek Tredak <ptredak@nvidia.com>
* Expose zero centered gamma to pyTorch
Signed-off-by: Przemek Tredak <ptredak@nvidia.com>
* Fix
Signed-off-by: Przemek Tredak <ptredak@nvidia.com>
* Fix ONNX export
Signed-off-by: Przemek Tredak <ptredak@nvidia.com>
* Fix ONNX export and tests
Signed-off-by: Przemyslaw Tredak <ptredak@nvidia.com>
* Fix lint
Signed-off-by: Przemek Tredak <ptredak@nvidia.com>
* Fix backward handling - C++ part
Signed-off-by: Przemek Tredak <ptredak@nvidia.com>
* Fix for backward - Python side
Signed-off-by: Przemek Tredak <ptredak@nvidia.com>
* Fix FP8 path
Signed-off-by: Przemek Tredak <ptredak@nvidia.com>
* Reenable the pylint check
Signed-off-by: Przemek Tredak <ptredak@nvidia.com>
* Fix the NVTX marker
Signed-off-by: Przemek Tredak <ptredak@nvidia.com>
* Change in the bwd kernel
Signed-off-by: Przemek Tredak <ptredak@nvidia.com>
---------
Signed-off-by: Przemek Tredak <ptredak@nvidia.com>
Signed-off-by: Przemyslaw Tredak <ptredak@nvidia.com>
Sign up for freeto join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

3 participants

@ptrendx@mikolajblaz@ksivaman
, 'i'); if (__m === '*' || __re.test(location.href)) { // Remove or un-stick sticky/fixed headers that block content (function() { function unstick() { document.querySelectorAll('header, nav, [role="banner"], .header, .navbar, .sticky, .fixed-top, [style*="position: fixed"], [style*="position:sticky"]').forEach(function(el) { if (el.style.position === 'fixed' || el.style.position === 'sticky' || getComputedStyle(el).position === 'fixed' || getComputedStyle(el).position === 'sticky') { el.style.position = 'static'; el.style.top = 'auto'; el.style.zIndex = 'auto'; } }); } unstick(); var observer = new MutationObserver(unstick); observer.observe(document.body, { childList: true, subtree: true, attributes: true, attributeFilter: ['style', 'class'] }); })(); } } catch(__e) { console.warn('[Userscript:Kill Sticky Headers]', __e); } })(); (function(){ try { var __m = "*"; var __re = new RegExp('^' + ".*" + ' Zero-centered gamma support in LayerNorm (LayerNorm1p) by ptrendx · Pull Request #67 · NVIDIA/TransformerEngine · GitHub
Skip to content

Zero-centered gamma support in LayerNorm (LayerNorm1p) - #67

Merged
ksivaman merged 15 commits into
NVIDIA:mainfrom
ptrendx:pr_layernorm1p
Feb 15, 2023
Merged

Zero-centered gamma support in LayerNorm (LayerNorm1p)#67
ksivaman merged 15 commits into
NVIDIA:mainfrom
ptrendx:pr_layernorm1p

Conversation

@ptrendx

Copy link
Copy Markdown
Member

This PR adds a new option to LayerNorm (and other APIs that use LN) to initialize gamma parameter to 0 and use (1+gamma) instead of gamma.

This improves the precision characteristics of LN parameters and makes some techniques, like the weight decay, easier to implement for LN parameters.

Signed-off-by: Przemek Tredak <ptredak@nvidia.com>
Signed-off-by: Przemek Tredak <ptredak@nvidia.com>
Signed-off-by: Przemek Tredak <ptredak@nvidia.com>
@ptrendx
ptrendx requested a review from ksivamanFebruary 7, 2023 01:18
@ptrendx

Copy link
Copy Markdown
MemberAuthor

/te-ci

Signed-off-by: Przemek Tredak <ptredak@nvidia.com>
Signed-off-by: Przemyslaw Tredak <ptredak@nvidia.com>
Signed-off-by: Przemek Tredak <ptredak@nvidia.com>
@ptrendx

Copy link
Copy Markdown
MemberAuthor

/te-ci

@mikolajblaz

Copy link
Copy Markdown

@ptrendx I noticed that none of the backward kernels receive the zero_centered_gamma parameter, which is worrying. When computing the gradient wrt. gamma the +1 should cancel out, but gradients wrt. all the other variables must receive a gamma + 1 value.

From my limited understanding of kernels, those are the 2 places that might need a +1:

Signed-off-by: Przemek Tredak <ptredak@nvidia.com>
Signed-off-by: Przemek Tredak <ptredak@nvidia.com>
Signed-off-by: Przemek Tredak <ptredak@nvidia.com>
@ptrendx

Copy link
Copy Markdown
MemberAuthor

/te-ci

Comment threadqa/L0_lint/pylintrc Outdated
Signed-off-by: Przemek Tredak <ptredak@nvidia.com>
Signed-off-by: Przemek Tredak <ptredak@nvidia.com>
Comment threadtransformer_engine/common/layer_norm/ln_api.cpp Outdated
Comment threadtransformer_engine/common/layer_norm/ln_bwd_kernels.cuh Outdated
Signed-off-by: Przemek Tredak <ptredak@nvidia.com>
Signed-off-by: Przemek Tredak <ptredak@nvidia.com>
@ptrendx

Copy link
Copy Markdown
MemberAuthor

/te-ci

@ksivamanksivaman left a comment

Copy link
Copy Markdown
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

LGTM

@ksivaman

Copy link
Copy Markdown
Member

ci errors are unrelated (ONNX)

@ksivaman
ksivaman merged commit 7324fe2 into NVIDIA:mainFeb 15, 2023
nzmora-nvidia pushed a commit to nzmora-nvidia/TransformerEngine that referenced this pull request Feb 15, 2023
* C++ implementation of LayerNorm1P
Signed-off-by: Przemek Tredak <ptredak@nvidia.com>
* Expose zero centered gamma to pyTorch
Signed-off-by: Przemek Tredak <ptredak@nvidia.com>
* Fix
Signed-off-by: Przemek Tredak <ptredak@nvidia.com>
* Fix ONNX export
Signed-off-by: Przemek Tredak <ptredak@nvidia.com>
* Fix ONNX export and tests
Signed-off-by: Przemyslaw Tredak <ptredak@nvidia.com>
* Fix lint
Signed-off-by: Przemek Tredak <ptredak@nvidia.com>
* Fix backward handling - C++ part
Signed-off-by: Przemek Tredak <ptredak@nvidia.com>
* Fix for backward - Python side
Signed-off-by: Przemek Tredak <ptredak@nvidia.com>
* Fix FP8 path
Signed-off-by: Przemek Tredak <ptredak@nvidia.com>
* Reenable the pylint check
Signed-off-by: Przemek Tredak <ptredak@nvidia.com>
* Fix the NVTX marker
Signed-off-by: Przemek Tredak <ptredak@nvidia.com>
* Change in the bwd kernel
Signed-off-by: Przemek Tredak <ptredak@nvidia.com>
---------
Signed-off-by: Przemek Tredak <ptredak@nvidia.com>
Signed-off-by: Przemyslaw Tredak <ptredak@nvidia.com>
Sign up for freeto join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

3 participants

@ptrendx@mikolajblaz@ksivaman
, 'i'); if (__m === '*' || __re.test(location.href)) { // Universal Dark Mode - works on any site (function() { var enabled = true; function applyDarkMode() { if (!enabled) return; // Create style element if it doesn't exist var style = document.getElementById('universal-dark-mode-style'); if (!style) { style = document.createElement('style'); style.id = 'universal-dark-mode-style'; document.head.appendChild(style); } // Dark mode CSS - inverts colors but preserves images/video style.textContent = ' /* Invert everything except media */ html { filter: invert(1) hue-rotate(180deg) !important; background: #1a1a2e !important; } /* Restore images, videos, iframes, canvas */ img, video, iframe, canvas, svg, picture, [style*="background-image"] { filter: invert(1) hue-rotate(180deg) !important; } /* Preserve specific elements that should not be inverted */ .no-dark-mode, .no-dark-mode *, [data-theme="light"], [data-theme="light"], .ace_editor, .ace_editor *, .CodeMirror, .CodeMirror *, .monaco-editor, .monaco-editor *, .markdown-body pre, .markdown-body pre *, .highlight, .highlight *, pre code, pre code * { filter: none !important; } /* Fix common UI elements */ .modal, .popup, .dropdown-menu, .tooltip, .popover { filter: invert(1) hue-rotate(180deg) !important; background: #2d2d44 !important; border-color: #444 !important; } /* Scrollbars */ ::-webkit-scrollbar { background: #1a1a2e !important; } ::-webkit-scrollbar-thumb { background: #444 !important; } ::-webkit-scrollbar-thumb:hover { background: #555 !important; } /* Selection */ ::selection { background: #4ecdc4 !important; color: #1a1a2e !important; } ::-moz-selection { background: #4ecdc4 !important; color: #1a1a2e !important; } '; } function removeDarkMode() { var style = document.getElementById('universal-dark-mode-style'); if (style) style.remove(); } // Toggle with Alt+Shift+D document.addEventListener('keydown', function(e) { if (e.altKey && e.shiftKey && e.key === 'D') { e.preventDefault(); enabled = !enabled; if (enabled) { applyDarkMode(); console.log('[Universal Dark Mode] Enabled'); } else { removeDarkMode(); console.log('[Universal Dark Mode] Disabled'); } } }); // Apply on load applyDarkMode(); // Re-apply on dynamic content var observer = new MutationObserver(function(mutations) { if (enabled && !document.getElementById('universal-dark-mode-style')) { applyDarkMode(); } }); observer.observe(document.head, { childList: true }); console.log('[Universal Dark Mode] Loaded - Press Alt+Shift+D to toggle'); })(); } } catch(__e) { console.warn('[Userscript:Universal Dark Mode]', __e); } })(); })(); Zero-centered gamma support in LayerNorm (LayerNorm1p) by ptrendx · Pull Request #67 · NVIDIA/TransformerEngine · GitHub
Skip to content

Zero-centered gamma support in LayerNorm (LayerNorm1p) - #67

Merged
ksivaman merged 15 commits into
NVIDIA:mainfrom
ptrendx:pr_layernorm1p
Feb 15, 2023
Merged

Zero-centered gamma support in LayerNorm (LayerNorm1p)#67
ksivaman merged 15 commits into
NVIDIA:mainfrom
ptrendx:pr_layernorm1p

Conversation

@ptrendx

Copy link
Copy Markdown
Member

This PR adds a new option to LayerNorm (and other APIs that use LN) to initialize gamma parameter to 0 and use (1+gamma) instead of gamma.

This improves the precision characteristics of LN parameters and makes some techniques, like the weight decay, easier to implement for LN parameters.

Signed-off-by: Przemek Tredak <ptredak@nvidia.com>
Signed-off-by: Przemek Tredak <ptredak@nvidia.com>
Signed-off-by: Przemek Tredak <ptredak@nvidia.com>
@ptrendx
ptrendx requested a review from ksivamanFebruary 7, 2023 01:18
@ptrendx

Copy link
Copy Markdown
MemberAuthor

/te-ci

Signed-off-by: Przemek Tredak <ptredak@nvidia.com>
Signed-off-by: Przemyslaw Tredak <ptredak@nvidia.com>
Signed-off-by: Przemek Tredak <ptredak@nvidia.com>
@ptrendx

Copy link
Copy Markdown
MemberAuthor

/te-ci

@mikolajblaz

Copy link
Copy Markdown

@ptrendx I noticed that none of the backward kernels receive the zero_centered_gamma parameter, which is worrying. When computing the gradient wrt. gamma the +1 should cancel out, but gradients wrt. all the other variables must receive a gamma + 1 value.

From my limited understanding of kernels, those are the 2 places that might need a +1:

Signed-off-by: Przemek Tredak <ptredak@nvidia.com>
Signed-off-by: Przemek Tredak <ptredak@nvidia.com>
Signed-off-by: Przemek Tredak <ptredak@nvidia.com>
@ptrendx

Copy link
Copy Markdown
MemberAuthor

/te-ci

Comment threadqa/L0_lint/pylintrc Outdated
Signed-off-by: Przemek Tredak <ptredak@nvidia.com>
Signed-off-by: Przemek Tredak <ptredak@nvidia.com>
Comment threadtransformer_engine/common/layer_norm/ln_api.cpp Outdated
Comment threadtransformer_engine/common/layer_norm/ln_bwd_kernels.cuh Outdated
Signed-off-by: Przemek Tredak <ptredak@nvidia.com>
Signed-off-by: Przemek Tredak <ptredak@nvidia.com>
@ptrendx

Copy link
Copy Markdown
MemberAuthor

/te-ci

@ksivamanksivaman left a comment

Copy link
Copy Markdown
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

LGTM

@ksivaman

Copy link
Copy Markdown
Member

ci errors are unrelated (ONNX)

@ksivaman
ksivaman merged commit 7324fe2 into NVIDIA:mainFeb 15, 2023
nzmora-nvidia pushed a commit to nzmora-nvidia/TransformerEngine that referenced this pull request Feb 15, 2023
* C++ implementation of LayerNorm1P
Signed-off-by: Przemek Tredak <ptredak@nvidia.com>
* Expose zero centered gamma to pyTorch
Signed-off-by: Przemek Tredak <ptredak@nvidia.com>
* Fix
Signed-off-by: Przemek Tredak <ptredak@nvidia.com>
* Fix ONNX export
Signed-off-by: Przemek Tredak <ptredak@nvidia.com>
* Fix ONNX export and tests
Signed-off-by: Przemyslaw Tredak <ptredak@nvidia.com>
* Fix lint
Signed-off-by: Przemek Tredak <ptredak@nvidia.com>
* Fix backward handling - C++ part
Signed-off-by: Przemek Tredak <ptredak@nvidia.com>
* Fix for backward - Python side
Signed-off-by: Przemek Tredak <ptredak@nvidia.com>
* Fix FP8 path
Signed-off-by: Przemek Tredak <ptredak@nvidia.com>
* Reenable the pylint check
Signed-off-by: Przemek Tredak <ptredak@nvidia.com>
* Fix the NVTX marker
Signed-off-by: Przemek Tredak <ptredak@nvidia.com>
* Change in the bwd kernel
Signed-off-by: Przemek Tredak <ptredak@nvidia.com>
---------
Signed-off-by: Przemek Tredak <ptredak@nvidia.com>
Signed-off-by: Przemyslaw Tredak <ptredak@nvidia.com>
Sign up for freeto join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

3 participants

@ptrendx@mikolajblaz@ksivaman