Skip to content

Pull requests: karpathy/llm.c

New pull request New
Clear current search query, filters, and sorts
119 Open 491 Closed
119 Open 491 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Reviews
Filter by reviews
No reviews Review required Approved review Changes requested
Assignee
Filter by who’s assigned
Assigned to nobody Loading
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Pull requests list

Add option to remove biases
#675 opened Jul 10, 2024 by gordicaleksa Loading…
3
Recompute mlp
#676 opened Jul 11, 2024 by ngc92 Loading…
-pm -> -pi: typo in error_usage
#765 opened Sep 22, 2024 by thundergolfer Loading…
Verify vocab is padded before reshaping
#782 opened Oct 23, 2024 by austinleedavis Loading…
Improve tanh derivative in backward gelu
#307 opened Apr 30, 2024 by akbariyeh Loading…
1
Updated adamw to use packed data types
#303 opened Apr 30, 2024 by ChrisDryden Loading…
17
fp16 buffers for ADAM
#289 opened Apr 29, 2024 by ngc92 Loading…
4
Update README.md with prerequisite of libomp
#691 opened Jul 17, 2024 by nzhang Loading…
Major FP32 llm.c improvements/refactoring/etc.
#696 opened Jul 18, 2024 by ademeure Loading…
Add optimized GPU kernels for encoder_backward using shared memory
#658 opened Jul 1, 2024 by vyom1611 Loading…
4
Update download_starter_pack.sh
#758 opened Sep 18, 2024 by dongrixinyu Loading…
add batch limit to 124m script to prevent infinite loop
#704 opened Jul 20, 2024 by varun-a10ai Loading…
multi-threaded model initialization
#737 opened Aug 12, 2024 by ngc92 Loading…
2
log with LINE and FILE for better addressing.
#746 opened Aug 22, 2024 by NEWPLAN Loading…
1
[WIP] initial curand implementation for model init
#741 opened Aug 13, 2024 by ngc92 Loading…
1
check libnccl instead of nccl to be more reliable
#742 opened Aug 14, 2024 by dengl11 Loading…
Experimenting with global instantiation for the layouts
#347 opened May 3, 2024 by ChrisDryden • Draft
GELU Fusion with cuBLASLt (SLOWER because it only merges in FP16 mode, not BF16/FP32...)
#338 opened May 3, 2024 by ademeure • Draft
Added A10 to mfu.h
#621 opened Jun 20, 2024 by tiehexue Loading…
3
Clarified installing CUDNN front-end headers and arch linux install instructs
#608 opened Jun 18, 2024 by bgorlick Loading…
1
Llama RoPE Forward Kernels
#607 opened Jun 17, 2024 by AndreSlavescu Loading…
gpt2_forward adding CUDA streams with events for async layered operations, cache prefetching for efficient data access with high temporal locality
#610 opened Jun 18, 2024 by bgorlick Loading…
1
Enhance gradient norm calc in gpt2_update: reuse variables, clarify first pass logic, improve condition handling
#609 opened Jun 18, 2024 by bgorlick Loading…
Add SwiGLU support
#718 opened Jul 29, 2024 by gordicaleksa Loading…
1
Faster GELU forward & backward using MUFU.TANH for SM7.5+
#721 opened Jul 31, 2024 by ademeure Loading…
4
ProTip! Add no:assignee to see everything that’s not assigned.