Skip to content

Pull requests: karpathy/llm.c

New pull request New
72 Open 313 Closed
72 Open 313 Closed
Author
Filter by author
Label
Filter by label
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Milestones
Filter by milestone
Reviews
Filter by reviews
No reviews Review required Approved review Changes requested
Assignee
Filter by who’s assigned
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Pull requests list

Testability
#523 opened Jun 2, 2024 by ngc92 • Draft
Add master weights to resume state
#522 opened Jun 2, 2024 by gordicaleksa Loading…
2
Replaced parameter B with the total parameters calculated outside of the kernel
#521 opened Jun 2, 2024 by ChrisDryden Loading…
Removing B in encoder and replacing with calculated N in kernel
#520 opened Jun 2, 2024 by ChrisDryden Loading…
Fix mem leak
#519 opened Jun 2, 2024 by gordicaleksa Loading…
Generalize MFU logic to common non-A100 GPUs
#518 opened Jun 2, 2024 by gordicaleksa Loading…
3
add edu fineweb support, with 10B and 100B version
#517 opened Jun 2, 2024 by eliebak Loading…
5
Add clarification on Box-Muller
#516 opened Jun 2, 2024 by gordicaleksa Loading…
Use local params for num blocks in adamw_kernel3
#515 opened Jun 2, 2024 by gordicaleksa Loading…
fix compilation with older nvcc
#514 opened Jun 2, 2024 by ngc92 Loading…
Added packed layernorm_forward
#513 opened Jun 2, 2024 by ChrisDryden Loading…
Remove redundant CPU computation in encoder bwd
#512 opened Jun 1, 2024 by gordicaleksa Loading…
Benchmark modal script revamped - profiling and external libraries (Issue #504)
#510 opened Jun 1, 2024 by vyom1611 Loading…
adding wsd schedule with (1-sqrt) decay
#508 opened Jun 1, 2024 by eliebak Loading…
3
Added script to download all of the tokenized fineweb100B data from huggingface
#507 opened May 31, 2024 by ChrisDryden • Draft
3
Added additional layernorm forward kernel that does not recalculate mean and rstd
#506 opened May 31, 2024 by ChrisDryden Loading…
Added constexpr for blocksizes to optimize compilation
#505 opened May 31, 2024 by ChrisDryden Loading…
Add DockerFile
#501 opened May 30, 2024 by banyan-god Loading…
Realtime training visualization using wandb
#489 opened May 29, 2024 by chinthysl Loading…
6
MFU for other GPUs
#486 opened May 28, 2024 by ngc92 Loading…
3
Trigger CI template
#483 opened May 28, 2024 by rosslwheeler Loading…
Added kernel development file for permute_backwards
#477 opened May 27, 2024 by ChrisDryden Loading…
1
[WIP - Fix] Add assert for layernorm kernel 8
#472 opened May 27, 2024 by lancerts • Draft
5
train_gpt2.c: Add gpt2_write_to_checkpoint method
#467 opened May 26, 2024 by faxe1008 Loading…
.gitignore: ignore more for windows devs
#466 opened May 26, 2024 by nietras Loading…
ProTip! Type g p on any issue or pull request to go back to the pull request listing page.