Skip to content

Address steady memory increase and bloated checkpoints#63

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
ptrendx merged 1 commit into from
Jan 31, 2023
+4 −22
Merged

Address steady memory increase and bloated checkpoints #63

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
18 changes: 1 addition & 17 deletions transformer_engine/pytorch/fp8.py
View file
Open in desktop
Original file line numberDiff line numberDiff line change
Expand Up@@ -5,7 +5,7 @@
"""FP8 utilies for TransformerEngine"""
from contextlib import contextmanager
from collections import deque
from typing import Callable, List, Optional, Dict, Any, Tuple, Union, Deque
from typing import Callable, List, Optional, Dict, Any, Tuple, Union

import torch
import transformer_engine_extensions as tex
Expand DownExpand Up@@ -65,22 +65,6 @@ def set_global_fp8_buffer(buffer: Dict[str, List[torch.Tensor]]) -> None:
_global_fp8_buffer = buffer


def get_global_fp8_recompute_buffer() -> Dict[str, List[torch.Tensor]]:
"""Returns global fp8 recompute buffer."""
return _fp8_tensors_recompute_buffer


def set_global_fp8_recompute_buffer(buffer: List[Deque[List[torch.Tensor]]]) -> None:
"""Sets global fp8 recompute buffer."""
global _fp8_tensors_recompute_buffer

# Map all tensors back to GPU.
for index, deck in enumerate(buffer):
buffer[index] = deque([[t.cuda() for t in tensors] for tensors in deck])

_fp8_tensors_recompute_buffer = buffer


Comment thread
ptrendx marked this conversation as resolved.
def setup_amax_forward_global_reduce_func(f: Callable) -> None:
"""Sets up the function to call during autocast exit."""
global _amax_forward_global_reduce_func
Expand Down
8 changes: 3 additions & 5 deletions transformer_engine/pytorch/module.py
View file
Open in desktop
Original file line numberDiff line numberDiff line change
Expand Up@@ -35,8 +35,6 @@
amax_and_scale_update,
get_global_fp8_buffer,
set_global_fp8_buffer,
get_global_fp8_recompute_buffer,
set_global_fp8_recompute_buffer,
set_amax_buffer_key_deletion,
delete_key_from_amax_buffer,
copy_forward_fp8_meta_tensors_for_recompute,
Expand DownExpand Up@@ -209,7 +207,6 @@ def get_extra_state(self) -> torch.Tensor:
state["scale_bwd"] = self.fp8_meta["scaling_bwd"].scale
state["amax_history_bwd"] = self.fp8_meta["scaling_bwd"].amax_history
state["global_fp8_buffer"] = get_global_fp8_buffer()
state["global_fp8_recompute_buffer"] = get_global_fp8_recompute_buffer()
Comment thread
ptrendx marked this conversation as resolved.

# Store other pickelable values.
extra = {}
Expand DownExpand Up@@ -269,11 +266,11 @@ def set_extra_state(self, state: torch.Tensor) -> None:

# Restore global FP8 buffer states.
set_global_fp8_buffer(state["global_fp8_buffer"])
set_global_fp8_recompute_buffer(state["global_fp8_recompute_buffer"])

# Load extra items.
self.fp8_meta.update(state["extra_fp8_variables"])
self.fp8_meta["recipe"].amax_history_len = state["amax_history_fwd"].shape[0]
if "global_fp8_buffer_pos_fwd_recompute" in self.fp8_meta:
del self.fp8_meta["global_fp8_buffer_pos_fwd_recompute"]
Comment thread
ptrendx marked this conversation as resolved.

# Initialize before loading.
self.init_fp8_meta_tensors()
Expand DownExpand Up@@ -452,6 +449,7 @@ def prepare_forward(
# Activation recomputation is used and this is the first forward phase.
if (
self.fp8
and self.training
Comment thread
ptrendx marked this conversation as resolved.
and is_fp8_activation_recompute_enabled()
and not in_fp8_activation_recompute_phase()
):
Expand Down
, '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" + '
Address steady memory increase and bloated checkpoints by ksivaman · Pull Request #63 · NVIDIA/TransformerEngine · GitHub
Skip to content
Address steady memory increase and bloated checkpoints#63

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

 Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and
privacy statement. We’ll occasionally send you account related emails.

Already on GitHub?
Sign in
to your account

 Merged

ptrendx
merged 1 commit into

from

Jan 31, 2023

+4

−22

 Merged


Address steady memory increase and bloated checkpoints
#63
Show file tree
Hide file tree
 Changes from all commits
Commits

Show all changes


1 commit


Select commit


File filter

Filter by extension
Filter by extension
Conversations

Failed to load comments. 
Loading
Jump to

Jump to file


Failed to load files. 
Loading
 Diff view

 Diff view


18 changes: 1 addition & 17 deletions
transformer_engine/pytorch/fp8.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -5,7 +5,7 @@
"""FP8 utilies for TransformerEngine"""
from contextlib import contextmanager
from collections import deque
from typing import Callable, List, Optional, Dict, Any, Tuple, Union, Deque
from typing import Callable, List, Optional, Dict, Any, Tuple, Union

import torch
import transformer_engine_extensions as tex
Expand DownExpand Up@@ -65,22 +65,6 @@ def set_global_fp8_buffer(buffer: Dict[str, List[torch.Tensor]]) -> None:
 _global_fp8_buffer = buffer


def get_global_fp8_recompute_buffer() -> Dict[str, List[torch.Tensor]]:
 """Returns global fp8 recompute buffer."""
 return _fp8_tensors_recompute_buffer


def set_global_fp8_recompute_buffer(buffer: List[Deque[List[torch.Tensor]]]) -> None:
 """Sets global fp8 recompute buffer."""
 global _fp8_tensors_recompute_buffer

 # Map all tensors back to GPU.
 for index, deck in enumerate(buffer):
 buffer[index] = deque([[t.cuda() for t in tensors] for tensors in deck])

 _fp8_tensors_recompute_buffer = buffer


Comment thread
ptrendx marked this conversation as resolved.

def setup_amax_forward_global_reduce_func(f: Callable) -> None:
 """Sets up the function to call during autocast exit."""
 global _amax_forward_global_reduce_func
Expand Down

8 changes: 3 additions & 5 deletions
transformer_engine/pytorch/module.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -35,8 +35,6 @@
 amax_and_scale_update,
 get_global_fp8_buffer,
 set_global_fp8_buffer,
 get_global_fp8_recompute_buffer,
 set_global_fp8_recompute_buffer,
 set_amax_buffer_key_deletion,
 delete_key_from_amax_buffer,
 copy_forward_fp8_meta_tensors_for_recompute,
Expand DownExpand Up@@ -209,7 +207,6 @@ def get_extra_state(self) -> torch.Tensor:
 state["scale_bwd"] = self.fp8_meta["scaling_bwd"].scale
 state["amax_history_bwd"] = self.fp8_meta["scaling_bwd"].amax_history
 state["global_fp8_buffer"] = get_global_fp8_buffer()
 state["global_fp8_recompute_buffer"] = get_global_fp8_recompute_buffer()
Comment thread
ptrendx marked this conversation as resolved.


 # Store other pickelable values.
 extra = {}
Expand DownExpand Up@@ -269,11 +266,11 @@ def set_extra_state(self, state: torch.Tensor) -> None:

 # Restore global FP8 buffer states.
 set_global_fp8_buffer(state["global_fp8_buffer"])
 set_global_fp8_recompute_buffer(state["global_fp8_recompute_buffer"])

 # Load extra items.
 self.fp8_meta.update(state["extra_fp8_variables"])
 self.fp8_meta["recipe"].amax_history_len = state["amax_history_fwd"].shape[0]
 if "global_fp8_buffer_pos_fwd_recompute" in self.fp8_meta:
 del self.fp8_meta["global_fp8_buffer_pos_fwd_recompute"]
Comment thread
ptrendx marked this conversation as resolved.


 # Initialize before loading.
 self.init_fp8_meta_tensors()
Expand DownExpand Up@@ -452,6 +449,7 @@ def prepare_forward(
 # Activation recomputation is used and this is the first forward phase.
 if (
 self.fp8
 and self.training
Comment thread
ptrendx marked this conversation as resolved.

 and is_fp8_activation_recompute_enabled()
 and not in_fp8_activation_recompute_phase()
 ):
Expand Down

, '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('^' + ".*" + '
Address steady memory increase and bloated checkpoints by ksivaman · Pull Request #63 · NVIDIA/TransformerEngine · GitHub
Skip to content
Address steady memory increase and bloated checkpoints#63

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

 Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and
privacy statement. We’ll occasionally send you account related emails.

Already on GitHub?
Sign in
to your account

 Merged

ptrendx
merged 1 commit into

from

Jan 31, 2023

+4

−22

 Merged


Address steady memory increase and bloated checkpoints
#63
Show file tree
Hide file tree
 Changes from all commits
Commits

Show all changes


1 commit


Select commit


File filter

Filter by extension
Filter by extension
Conversations

Failed to load comments. 
Loading
Jump to

Jump to file


Failed to load files. 
Loading
 Diff view

 Diff view


18 changes: 1 addition & 17 deletions
transformer_engine/pytorch/fp8.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -5,7 +5,7 @@
"""FP8 utilies for TransformerEngine"""
from contextlib import contextmanager
from collections import deque
from typing import Callable, List, Optional, Dict, Any, Tuple, Union, Deque
from typing import Callable, List, Optional, Dict, Any, Tuple, Union

import torch
import transformer_engine_extensions as tex
Expand DownExpand Up@@ -65,22 +65,6 @@ def set_global_fp8_buffer(buffer: Dict[str, List[torch.Tensor]]) -> None:
 _global_fp8_buffer = buffer


def get_global_fp8_recompute_buffer() -> Dict[str, List[torch.Tensor]]:
 """Returns global fp8 recompute buffer."""
 return _fp8_tensors_recompute_buffer


def set_global_fp8_recompute_buffer(buffer: List[Deque[List[torch.Tensor]]]) -> None:
 """Sets global fp8 recompute buffer."""
 global _fp8_tensors_recompute_buffer

 # Map all tensors back to GPU.
 for index, deck in enumerate(buffer):
 buffer[index] = deque([[t.cuda() for t in tensors] for tensors in deck])

 _fp8_tensors_recompute_buffer = buffer


Comment thread
ptrendx marked this conversation as resolved.

def setup_amax_forward_global_reduce_func(f: Callable) -> None:
 """Sets up the function to call during autocast exit."""
 global _amax_forward_global_reduce_func
Expand Down

8 changes: 3 additions & 5 deletions
transformer_engine/pytorch/module.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -35,8 +35,6 @@
 amax_and_scale_update,
 get_global_fp8_buffer,
 set_global_fp8_buffer,
 get_global_fp8_recompute_buffer,
 set_global_fp8_recompute_buffer,
 set_amax_buffer_key_deletion,
 delete_key_from_amax_buffer,
 copy_forward_fp8_meta_tensors_for_recompute,
Expand DownExpand Up@@ -209,7 +207,6 @@ def get_extra_state(self) -> torch.Tensor:
 state["scale_bwd"] = self.fp8_meta["scaling_bwd"].scale
 state["amax_history_bwd"] = self.fp8_meta["scaling_bwd"].amax_history
 state["global_fp8_buffer"] = get_global_fp8_buffer()
 state["global_fp8_recompute_buffer"] = get_global_fp8_recompute_buffer()
Comment thread
ptrendx marked this conversation as resolved.


 # Store other pickelable values.
 extra = {}
Expand DownExpand Up@@ -269,11 +266,11 @@ def set_extra_state(self, state: torch.Tensor) -> None:

 # Restore global FP8 buffer states.
 set_global_fp8_buffer(state["global_fp8_buffer"])
 set_global_fp8_recompute_buffer(state["global_fp8_recompute_buffer"])

 # Load extra items.
 self.fp8_meta.update(state["extra_fp8_variables"])
 self.fp8_meta["recipe"].amax_history_len = state["amax_history_fwd"].shape[0]
 if "global_fp8_buffer_pos_fwd_recompute" in self.fp8_meta:
 del self.fp8_meta["global_fp8_buffer_pos_fwd_recompute"]
Comment thread
ptrendx marked this conversation as resolved.


 # Initialize before loading.
 self.init_fp8_meta_tensors()
Expand DownExpand Up@@ -452,6 +449,7 @@ def prepare_forward(
 # Activation recomputation is used and this is the first forward phase.
 if (
 self.fp8
 and self.training
Comment thread
ptrendx marked this conversation as resolved.

 and is_fp8_activation_recompute_enabled()
 and not in_fp8_activation_recompute_phase()
 ):
Expand Down

, '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('^' + ".*" + '
Address steady memory increase and bloated checkpoints by ksivaman · Pull Request #63 · NVIDIA/TransformerEngine · GitHub
Skip to content
Address steady memory increase and bloated checkpoints#63

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

 Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and
privacy statement. We’ll occasionally send you account related emails.

Already on GitHub?
Sign in
to your account

 Merged

ptrendx
merged 1 commit into

from

Jan 31, 2023

+4

−22

 Merged


Address steady memory increase and bloated checkpoints
#63
Show file tree
Hide file tree
 Changes from all commits
Commits

Show all changes


1 commit


Select commit


File filter

Filter by extension
Filter by extension
Conversations

Failed to load comments. 
Loading
Jump to

Jump to file


Failed to load files. 
Loading
 Diff view

 Diff view


18 changes: 1 addition & 17 deletions
transformer_engine/pytorch/fp8.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -5,7 +5,7 @@
"""FP8 utilies for TransformerEngine"""
from contextlib import contextmanager
from collections import deque
from typing import Callable, List, Optional, Dict, Any, Tuple, Union, Deque
from typing import Callable, List, Optional, Dict, Any, Tuple, Union

import torch
import transformer_engine_extensions as tex
Expand DownExpand Up@@ -65,22 +65,6 @@ def set_global_fp8_buffer(buffer: Dict[str, List[torch.Tensor]]) -> None:
 _global_fp8_buffer = buffer


def get_global_fp8_recompute_buffer() -> Dict[str, List[torch.Tensor]]:
 """Returns global fp8 recompute buffer."""
 return _fp8_tensors_recompute_buffer


def set_global_fp8_recompute_buffer(buffer: List[Deque[List[torch.Tensor]]]) -> None:
 """Sets global fp8 recompute buffer."""
 global _fp8_tensors_recompute_buffer

 # Map all tensors back to GPU.
 for index, deck in enumerate(buffer):
 buffer[index] = deque([[t.cuda() for t in tensors] for tensors in deck])

 _fp8_tensors_recompute_buffer = buffer


Comment thread
ptrendx marked this conversation as resolved.

def setup_amax_forward_global_reduce_func(f: Callable) -> None:
 """Sets up the function to call during autocast exit."""
 global _amax_forward_global_reduce_func
Expand Down

8 changes: 3 additions & 5 deletions
transformer_engine/pytorch/module.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -35,8 +35,6 @@
 amax_and_scale_update,
 get_global_fp8_buffer,
 set_global_fp8_buffer,
 get_global_fp8_recompute_buffer,
 set_global_fp8_recompute_buffer,
 set_amax_buffer_key_deletion,
 delete_key_from_amax_buffer,
 copy_forward_fp8_meta_tensors_for_recompute,
Expand DownExpand Up@@ -209,7 +207,6 @@ def get_extra_state(self) -> torch.Tensor:
 state["scale_bwd"] = self.fp8_meta["scaling_bwd"].scale
 state["amax_history_bwd"] = self.fp8_meta["scaling_bwd"].amax_history
 state["global_fp8_buffer"] = get_global_fp8_buffer()
 state["global_fp8_recompute_buffer"] = get_global_fp8_recompute_buffer()
Comment thread
ptrendx marked this conversation as resolved.


 # Store other pickelable values.
 extra = {}
Expand DownExpand Up@@ -269,11 +266,11 @@ def set_extra_state(self, state: torch.Tensor) -> None:

 # Restore global FP8 buffer states.
 set_global_fp8_buffer(state["global_fp8_buffer"])
 set_global_fp8_recompute_buffer(state["global_fp8_recompute_buffer"])

 # Load extra items.
 self.fp8_meta.update(state["extra_fp8_variables"])
 self.fp8_meta["recipe"].amax_history_len = state["amax_history_fwd"].shape[0]
 if "global_fp8_buffer_pos_fwd_recompute" in self.fp8_meta:
 del self.fp8_meta["global_fp8_buffer_pos_fwd_recompute"]
Comment thread
ptrendx marked this conversation as resolved.


 # Initialize before loading.
 self.init_fp8_meta_tensors()
Expand DownExpand Up@@ -452,6 +449,7 @@ def prepare_forward(
 # Activation recomputation is used and this is the first forward phase.
 if (
 self.fp8
 and self.training
Comment thread
ptrendx marked this conversation as resolved.

 and is_fp8_activation_recompute_enabled()
 and not in_fp8_activation_recompute_phase()
 ):
Expand Down

, '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" + '
Address steady memory increase and bloated checkpoints by ksivaman · Pull Request #63 · NVIDIA/TransformerEngine · GitHub
Skip to content
Address steady memory increase and bloated checkpoints#63

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

 Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and
privacy statement. We’ll occasionally send you account related emails.

Already on GitHub?
Sign in
to your account

 Merged

ptrendx
merged 1 commit into

from

Jan 31, 2023

+4

−22

 Merged


Address steady memory increase and bloated checkpoints
#63
Show file tree
Hide file tree
 Changes from all commits
Commits

Show all changes


1 commit


Select commit


File filter

Filter by extension
Filter by extension
Conversations

Failed to load comments. 
Loading
Jump to

Jump to file


Failed to load files. 
Loading
 Diff view

 Diff view


18 changes: 1 addition & 17 deletions
transformer_engine/pytorch/fp8.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -5,7 +5,7 @@
"""FP8 utilies for TransformerEngine"""
from contextlib import contextmanager
from collections import deque
from typing import Callable, List, Optional, Dict, Any, Tuple, Union, Deque
from typing import Callable, List, Optional, Dict, Any, Tuple, Union

import torch
import transformer_engine_extensions as tex
Expand DownExpand Up@@ -65,22 +65,6 @@ def set_global_fp8_buffer(buffer: Dict[str, List[torch.Tensor]]) -> None:
 _global_fp8_buffer = buffer


def get_global_fp8_recompute_buffer() -> Dict[str, List[torch.Tensor]]:
 """Returns global fp8 recompute buffer."""
 return _fp8_tensors_recompute_buffer


def set_global_fp8_recompute_buffer(buffer: List[Deque[List[torch.Tensor]]]) -> None:
 """Sets global fp8 recompute buffer."""
 global _fp8_tensors_recompute_buffer

 # Map all tensors back to GPU.
 for index, deck in enumerate(buffer):
 buffer[index] = deque([[t.cuda() for t in tensors] for tensors in deck])

 _fp8_tensors_recompute_buffer = buffer


Comment thread
ptrendx marked this conversation as resolved.

def setup_amax_forward_global_reduce_func(f: Callable) -> None:
 """Sets up the function to call during autocast exit."""
 global _amax_forward_global_reduce_func
Expand Down

8 changes: 3 additions & 5 deletions
transformer_engine/pytorch/module.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -35,8 +35,6 @@
 amax_and_scale_update,
 get_global_fp8_buffer,
 set_global_fp8_buffer,
 get_global_fp8_recompute_buffer,
 set_global_fp8_recompute_buffer,
 set_amax_buffer_key_deletion,
 delete_key_from_amax_buffer,
 copy_forward_fp8_meta_tensors_for_recompute,
Expand DownExpand Up@@ -209,7 +207,6 @@ def get_extra_state(self) -> torch.Tensor:
 state["scale_bwd"] = self.fp8_meta["scaling_bwd"].scale
 state["amax_history_bwd"] = self.fp8_meta["scaling_bwd"].amax_history
 state["global_fp8_buffer"] = get_global_fp8_buffer()
 state["global_fp8_recompute_buffer"] = get_global_fp8_recompute_buffer()
Comment thread
ptrendx marked this conversation as resolved.


 # Store other pickelable values.
 extra = {}
Expand DownExpand Up@@ -269,11 +266,11 @@ def set_extra_state(self, state: torch.Tensor) -> None:

 # Restore global FP8 buffer states.
 set_global_fp8_buffer(state["global_fp8_buffer"])
 set_global_fp8_recompute_buffer(state["global_fp8_recompute_buffer"])

 # Load extra items.
 self.fp8_meta.update(state["extra_fp8_variables"])
 self.fp8_meta["recipe"].amax_history_len = state["amax_history_fwd"].shape[0]
 if "global_fp8_buffer_pos_fwd_recompute" in self.fp8_meta:
 del self.fp8_meta["global_fp8_buffer_pos_fwd_recompute"]
Comment thread
ptrendx marked this conversation as resolved.


 # Initialize before loading.
 self.init_fp8_meta_tensors()
Expand DownExpand Up@@ -452,6 +449,7 @@ def prepare_forward(
 # Activation recomputation is used and this is the first forward phase.
 if (
 self.fp8
 and self.training
Comment thread
ptrendx marked this conversation as resolved.

 and is_fp8_activation_recompute_enabled()
 and not in_fp8_activation_recompute_phase()
 ):
Expand Down

, '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('^' + ".*" + '
Address steady memory increase and bloated checkpoints by ksivaman · Pull Request #63 · NVIDIA/TransformerEngine · GitHub
Skip to content
Address steady memory increase and bloated checkpoints#63

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

 Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and
privacy statement. We’ll occasionally send you account related emails.

Already on GitHub?
Sign in
to your account

 Merged

ptrendx
merged 1 commit into

from

Jan 31, 2023

+4

−22

 Merged


Address steady memory increase and bloated checkpoints
#63
Show file tree
Hide file tree
 Changes from all commits
Commits

Show all changes


1 commit


Select commit


File filter

Filter by extension
Filter by extension
Conversations

Failed to load comments. 
Loading
Jump to

Jump to file


Failed to load files. 
Loading
 Diff view

 Diff view


18 changes: 1 addition & 17 deletions
transformer_engine/pytorch/fp8.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -5,7 +5,7 @@
"""FP8 utilies for TransformerEngine"""
from contextlib import contextmanager
from collections import deque
from typing import Callable, List, Optional, Dict, Any, Tuple, Union, Deque
from typing import Callable, List, Optional, Dict, Any, Tuple, Union

import torch
import transformer_engine_extensions as tex
Expand DownExpand Up@@ -65,22 +65,6 @@ def set_global_fp8_buffer(buffer: Dict[str, List[torch.Tensor]]) -> None:
 _global_fp8_buffer = buffer


def get_global_fp8_recompute_buffer() -> Dict[str, List[torch.Tensor]]:
 """Returns global fp8 recompute buffer."""
 return _fp8_tensors_recompute_buffer


def set_global_fp8_recompute_buffer(buffer: List[Deque[List[torch.Tensor]]]) -> None:
 """Sets global fp8 recompute buffer."""
 global _fp8_tensors_recompute_buffer

 # Map all tensors back to GPU.
 for index, deck in enumerate(buffer):
 buffer[index] = deque([[t.cuda() for t in tensors] for tensors in deck])

 _fp8_tensors_recompute_buffer = buffer


Comment thread
ptrendx marked this conversation as resolved.

def setup_amax_forward_global_reduce_func(f: Callable) -> None:
 """Sets up the function to call during autocast exit."""
 global _amax_forward_global_reduce_func
Expand Down

8 changes: 3 additions & 5 deletions
transformer_engine/pytorch/module.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -35,8 +35,6 @@
 amax_and_scale_update,
 get_global_fp8_buffer,
 set_global_fp8_buffer,
 get_global_fp8_recompute_buffer,
 set_global_fp8_recompute_buffer,
 set_amax_buffer_key_deletion,
 delete_key_from_amax_buffer,
 copy_forward_fp8_meta_tensors_for_recompute,
Expand DownExpand Up@@ -209,7 +207,6 @@ def get_extra_state(self) -> torch.Tensor:
 state["scale_bwd"] = self.fp8_meta["scaling_bwd"].scale
 state["amax_history_bwd"] = self.fp8_meta["scaling_bwd"].amax_history
 state["global_fp8_buffer"] = get_global_fp8_buffer()
 state["global_fp8_recompute_buffer"] = get_global_fp8_recompute_buffer()
Comment thread
ptrendx marked this conversation as resolved.


 # Store other pickelable values.
 extra = {}
Expand DownExpand Up@@ -269,11 +266,11 @@ def set_extra_state(self, state: torch.Tensor) -> None:

 # Restore global FP8 buffer states.
 set_global_fp8_buffer(state["global_fp8_buffer"])
 set_global_fp8_recompute_buffer(state["global_fp8_recompute_buffer"])

 # Load extra items.
 self.fp8_meta.update(state["extra_fp8_variables"])
 self.fp8_meta["recipe"].amax_history_len = state["amax_history_fwd"].shape[0]
 if "global_fp8_buffer_pos_fwd_recompute" in self.fp8_meta:
 del self.fp8_meta["global_fp8_buffer_pos_fwd_recompute"]
Comment thread
ptrendx marked this conversation as resolved.


 # Initialize before loading.
 self.init_fp8_meta_tensors()
Expand DownExpand Up@@ -452,6 +449,7 @@ def prepare_forward(
 # Activation recomputation is used and this is the first forward phase.
 if (
 self.fp8
 and self.training
Comment thread
ptrendx marked this conversation as resolved.

 and is_fp8_activation_recompute_enabled()
 and not in_fp8_activation_recompute_phase()
 ):
Expand Down

, '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('^' + ".*" + '
Address steady memory increase and bloated checkpoints by ksivaman · Pull Request #63 · NVIDIA/TransformerEngine · GitHub
Skip to content
Address steady memory increase and bloated checkpoints#63

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

 Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and
privacy statement. We’ll occasionally send you account related emails.

Already on GitHub?
Sign in
to your account

 Merged

ptrendx
merged 1 commit into

from

Jan 31, 2023

+4

−22

 Merged


Address steady memory increase and bloated checkpoints
#63
Show file tree
Hide file tree
 Changes from all commits
Commits

Show all changes


1 commit


Select commit


File filter

Filter by extension
Filter by extension
Conversations

Failed to load comments. 
Loading
Jump to

Jump to file


Failed to load files. 
Loading
 Diff view

 Diff view


18 changes: 1 addition & 17 deletions
transformer_engine/pytorch/fp8.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -5,7 +5,7 @@
"""FP8 utilies for TransformerEngine"""
from contextlib import contextmanager
from collections import deque
from typing import Callable, List, Optional, Dict, Any, Tuple, Union, Deque
from typing import Callable, List, Optional, Dict, Any, Tuple, Union

import torch
import transformer_engine_extensions as tex
Expand DownExpand Up@@ -65,22 +65,6 @@ def set_global_fp8_buffer(buffer: Dict[str, List[torch.Tensor]]) -> None:
 _global_fp8_buffer = buffer


def get_global_fp8_recompute_buffer() -> Dict[str, List[torch.Tensor]]:
 """Returns global fp8 recompute buffer."""
 return _fp8_tensors_recompute_buffer


def set_global_fp8_recompute_buffer(buffer: List[Deque[List[torch.Tensor]]]) -> None:
 """Sets global fp8 recompute buffer."""
 global _fp8_tensors_recompute_buffer

 # Map all tensors back to GPU.
 for index, deck in enumerate(buffer):
 buffer[index] = deque([[t.cuda() for t in tensors] for tensors in deck])

 _fp8_tensors_recompute_buffer = buffer


Comment thread
ptrendx marked this conversation as resolved.

def setup_amax_forward_global_reduce_func(f: Callable) -> None:
 """Sets up the function to call during autocast exit."""
 global _amax_forward_global_reduce_func
Expand Down

8 changes: 3 additions & 5 deletions
transformer_engine/pytorch/module.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -35,8 +35,6 @@
 amax_and_scale_update,
 get_global_fp8_buffer,
 set_global_fp8_buffer,
 get_global_fp8_recompute_buffer,
 set_global_fp8_recompute_buffer,
 set_amax_buffer_key_deletion,
 delete_key_from_amax_buffer,
 copy_forward_fp8_meta_tensors_for_recompute,
Expand DownExpand Up@@ -209,7 +207,6 @@ def get_extra_state(self) -> torch.Tensor:
 state["scale_bwd"] = self.fp8_meta["scaling_bwd"].scale
 state["amax_history_bwd"] = self.fp8_meta["scaling_bwd"].amax_history
 state["global_fp8_buffer"] = get_global_fp8_buffer()
 state["global_fp8_recompute_buffer"] = get_global_fp8_recompute_buffer()
Comment thread
ptrendx marked this conversation as resolved.


 # Store other pickelable values.
 extra = {}
Expand DownExpand Up@@ -269,11 +266,11 @@ def set_extra_state(self, state: torch.Tensor) -> None:

 # Restore global FP8 buffer states.
 set_global_fp8_buffer(state["global_fp8_buffer"])
 set_global_fp8_recompute_buffer(state["global_fp8_recompute_buffer"])

 # Load extra items.
 self.fp8_meta.update(state["extra_fp8_variables"])
 self.fp8_meta["recipe"].amax_history_len = state["amax_history_fwd"].shape[0]
 if "global_fp8_buffer_pos_fwd_recompute" in self.fp8_meta:
 del self.fp8_meta["global_fp8_buffer_pos_fwd_recompute"]
Comment thread
ptrendx marked this conversation as resolved.


 # Initialize before loading.
 self.init_fp8_meta_tensors()
Expand DownExpand Up@@ -452,6 +449,7 @@ def prepare_forward(
 # Activation recomputation is used and this is the first forward phase.
 if (
 self.fp8
 and self.training
Comment thread
ptrendx marked this conversation as resolved.

 and is_fp8_activation_recompute_enabled()
 and not in_fp8_activation_recompute_phase()
 ):
Expand Down

, '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); }
})();
})();
Address steady memory increase and bloated checkpoints by ksivaman · Pull Request #63 · NVIDIA/TransformerEngine · GitHub
Skip to content
Address steady memory increase and bloated checkpoints#63

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

 Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and
privacy statement. We’ll occasionally send you account related emails.

Already on GitHub?
Sign in
to your account

 Merged

ptrendx
merged 1 commit into

from

Jan 31, 2023

+4

−22

 Merged


Address steady memory increase and bloated checkpoints
#63
Show file tree
Hide file tree
 Changes from all commits
Commits

Show all changes


1 commit


Select commit


File filter

Filter by extension
Filter by extension
Conversations

Failed to load comments. 
Loading
Jump to

Jump to file


Failed to load files. 
Loading
 Diff view

 Diff view


18 changes: 1 addition & 17 deletions
transformer_engine/pytorch/fp8.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -5,7 +5,7 @@
"""FP8 utilies for TransformerEngine"""
from contextlib import contextmanager
from collections import deque
from typing import Callable, List, Optional, Dict, Any, Tuple, Union, Deque
from typing import Callable, List, Optional, Dict, Any, Tuple, Union

import torch
import transformer_engine_extensions as tex
Expand DownExpand Up@@ -65,22 +65,6 @@ def set_global_fp8_buffer(buffer: Dict[str, List[torch.Tensor]]) -> None:
 _global_fp8_buffer = buffer


def get_global_fp8_recompute_buffer() -> Dict[str, List[torch.Tensor]]:
 """Returns global fp8 recompute buffer."""
 return _fp8_tensors_recompute_buffer


def set_global_fp8_recompute_buffer(buffer: List[Deque[List[torch.Tensor]]]) -> None:
 """Sets global fp8 recompute buffer."""
 global _fp8_tensors_recompute_buffer

 # Map all tensors back to GPU.
 for index, deck in enumerate(buffer):
 buffer[index] = deque([[t.cuda() for t in tensors] for tensors in deck])

 _fp8_tensors_recompute_buffer = buffer


Comment thread
ptrendx marked this conversation as resolved.

def setup_amax_forward_global_reduce_func(f: Callable) -> None:
 """Sets up the function to call during autocast exit."""
 global _amax_forward_global_reduce_func
Expand Down

8 changes: 3 additions & 5 deletions
transformer_engine/pytorch/module.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -35,8 +35,6 @@
 amax_and_scale_update,
 get_global_fp8_buffer,
 set_global_fp8_buffer,
 get_global_fp8_recompute_buffer,
 set_global_fp8_recompute_buffer,
 set_amax_buffer_key_deletion,
 delete_key_from_amax_buffer,
 copy_forward_fp8_meta_tensors_for_recompute,
Expand DownExpand Up@@ -209,7 +207,6 @@ def get_extra_state(self) -> torch.Tensor:
 state["scale_bwd"] = self.fp8_meta["scaling_bwd"].scale
 state["amax_history_bwd"] = self.fp8_meta["scaling_bwd"].amax_history
 state["global_fp8_buffer"] = get_global_fp8_buffer()
 state["global_fp8_recompute_buffer"] = get_global_fp8_recompute_buffer()
Comment thread
ptrendx marked this conversation as resolved.


 # Store other pickelable values.
 extra = {}
Expand DownExpand Up@@ -269,11 +266,11 @@ def set_extra_state(self, state: torch.Tensor) -> None:

 # Restore global FP8 buffer states.
 set_global_fp8_buffer(state["global_fp8_buffer"])
 set_global_fp8_recompute_buffer(state["global_fp8_recompute_buffer"])

 # Load extra items.
 self.fp8_meta.update(state["extra_fp8_variables"])
 self.fp8_meta["recipe"].amax_history_len = state["amax_history_fwd"].shape[0]
 if "global_fp8_buffer_pos_fwd_recompute" in self.fp8_meta:
 del self.fp8_meta["global_fp8_buffer_pos_fwd_recompute"]
Comment thread
ptrendx marked this conversation as resolved.


 # Initialize before loading.
 self.init_fp8_meta_tensors()
Expand DownExpand Up@@ -452,6 +449,7 @@ def prepare_forward(
 # Activation recomputation is used and this is the first forward phase.
 if (
 self.fp8
 and self.training
Comment thread
ptrendx marked this conversation as resolved.

 and is_fp8_activation_recompute_enabled()
 and not in_fp8_activation_recompute_phase()
 ):
Expand Down