Skip to content

Pull requests: pytorch/FBGEMM

New pull request New
387 Open 3,057 Closed
387 Open 3,057 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
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Pull requests list

Add optional zero_start_index_M argument to triton fp8 rowwise quantization cla signed fb-exported
#3628 opened Jan 28, 2025 by jwfromm Loading…
3
finish #1808 cherry-pick, adjust interface cla signed fb-exported
#3627 opened Jan 28, 2025 by coconutruben Loading…
2
Fix calling numel on symbolic shapes issue cla signed fb-exported
#3621 opened Jan 27, 2025 by Microve Loading…
3
Partial revert of D66986498 cla signed fb-exported
#3620 opened Jan 27, 2025 by q10 Loading…
2
Re-land D67407935 (Optimized backward pass for ROCm devices, pt 2) ciflow/rocm cla signed fb-exported module: rocm
#3619 opened Jan 27, 2025 by q10 Loading…
3
Performance Optimization: Optimized TileShape Configuration for f8 cla signed
#3617 opened Jan 27, 2025 by MatrixAssembler Loading…
7
Fix handling of dynamic FP8 grouped gemm on Nvidia cla signed fb-exported
#3616 opened Jan 26, 2025 by jwfromm Loading…
2
Updating split_table_batched_embeddings_ops_training.py cla signed fb-exported
#3613 opened Jan 24, 2025 by basilwong Loading…
30
Replace runners prefix amz2023. (#2895) cla signed fb-exported module: rocm
#3612 opened Jan 24, 2025 by q10 Loading…
2
Port oss f16_fast_gemv into fbcode cla signed fb-exported
#3610 opened Jan 23, 2025 by YUNQIUGUO Loading…
7
Test out D68193920 cla signed fb-exported
#3606 opened Jan 23, 2025 by q10 Loading…
7
AdagradW cla signed fb-exported
#3605 opened Jan 23, 2025 by spcyppt Loading…
4
[fbgemm_gpu] Try nested ops namespaces cla signed
#3603 opened Jan 22, 2025 by q10 Loading…
1
Fix autodeps for torch/custom_class.h and use it in kv_tensor_wrapper_cpu (#677) cla signed fb-exported
#3596 opened Jan 22, 2025 by r-barnes Loading…
2
Performance Optimization: Optimized TileShape Configuration for bf16 and Mixed Formats cla signed
#3591 opened Jan 20, 2025 by MatrixAssembler Loading…
3
Support INT4 Dequant onto GPU for Seq INT TBE look up cla signed fb-exported
#3584 opened Jan 17, 2025 by faran928 Loading…
4
Return mixed_D default value to true cla signed
#3579 opened Jan 16, 2025 by avbokovoy Loading…
1
Update GenAI CK Version cla signed fb-exported
#3567 opened Jan 13, 2025 by jwfromm Loading…
2
Unifying TBE API using List (Backend) cla signed fb-exported
#3563 opened Jan 11, 2025 by spcyppt Loading…
6
Refactor FP8 grouped GEMM with dynamic and static versions cla signed fb-exported
#3561 opened Jan 10, 2025 by jiawenliu64 Loading…
9
Support FP8 grouped GEMM with rowwise scailing cla signed fb-exported
#3560 opened Jan 10, 2025 by jiawenliu64 Loading…
3
Expand tensor accessor checks cla signed fb-exported
#3559 opened Jan 10, 2025 by q10 Loading…
2
Switch dynamic FP8 grouped gemm to accept tensor inputs cla signed fb-exported
#3552 opened Jan 6, 2025 by jwfromm Loading…
2
Implement infrenece bag packing along D cla signed
#3541 opened Jan 3, 2025 by avbokovoy • Draft
1
env variable to select rounding mode cla signed fb-exported
#3515 opened Dec 19, 2024 by hhyuanf Loading…
6
ProTip! Exclude everything labeled bug with -label:bug.