Skip to content

Pull requests: HazyResearch/ThunderKittens

New pull request New
Clear current search query, filters, and sorts
16 Open 69 Closed
16 Open 69 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

added a docker container (only try on GPU wont work on CPU)
#146 opened Aug 24, 2025 by Kushagra481 Loading… updated Sep 17, 2025
Document and simplify fp16 -> fp8 conversion
#140 opened Aug 3, 2025 by melonedo Loading… updated Sep 15, 2025
Fix unit test Makefile bugs for A100 and 4090 results in linker failure due to cuda libraries missing
#145 opened Aug 20, 2025 by tomflinda Loading… updated Sep 15, 2025
40% build speedup: get torch and python include paths without subprocesses
#119 opened May 7, 2025 by technillogue Loading… updated Sep 15, 2025
Do not pass l_vec and o to mha_forward in h100_bench
#92 opened Feb 19, 2025 by acforvs Loading… updated Sep 15, 2025
1
global_to_shared.cuh row accessing fixes
#95 opened Feb 21, 2025 by dylanllim Loading… updated Sep 15, 2025
Add Semaphore Support for cp.async loads (Non-TMA Load Patterns)
#97 opened Mar 5, 2025 by SohamGovande Loading… updated Sep 15, 2025
Use -gencode instead of -arch in mla_decode
#126 opened Jun 6, 2025 by lucifer1004 Loading… updated Sep 15, 2025
1
I created a website to write documentation!
#89 opened Feb 14, 2025 by prateekshukla1108 Loading… updated Sep 15, 2025
Gpt2
#103 opened Mar 17, 2025 by oleitersdorf Loading… updated Sep 15, 2025
1
Remove unnecessary device and stream syncs
#129 opened Jun 15, 2025 by Edenzzzz Loading… updated Sep 15, 2025
10
batch matrix multiply kernel
#94 opened Feb 19, 2025 by technillogue • Draft updated Sep 15, 2025
implement group gemm for contiguous case
#136 opened Jul 22, 2025 by XiaobingSuper Loading… updated Sep 15, 2025
5
Added LCSF template implementation support for FlashAttention Backward.
#135 opened Jul 22, 2025 by KuangjuX Loading… updated Sep 15, 2025
2 tasks done
5
Add Implementation of Native Sparse Attention
#137 opened Jul 22, 2025 by yukavio Loading… updated Sep 15, 2025
Remove redundant register declarations.
#134 opened Jul 22, 2025 by KuangjuX Loading… updated Sep 15, 2025
ProTip! Adding no:label will show everything without a label.