Skip to content

Pull requests: pytorch/FBGEMM

New pull request New
587 Open 4,335 Closed
587 Open 4,335 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

Update to batch processing delta update for kvzch and fix table idx issue. cla signed fb-exported meta-exported
#5148 opened Nov 18, 2025 by EddyLXJ Loading…
1
shortcut for merge_pooled_embedding cla signed fb-exported meta-exported
#5147 opened Nov 18, 2025 by garroud Loading…
1
Add support rowwise_adagrad_wtith_counter on CPU cla signed fb-exported meta-exported
#5146 opened Nov 18, 2025 by gchalump Loading…
1
[fbgemm_gpu] Enable CUDA 13 builds in OSS cla signed
#5143 opened Nov 17, 2025 by q10 Loading…
1
Adding support for top_k=8 to index_shuffling moe kernel cla signed fb-exported meta-exported
#5142 opened Nov 17, 2025 by metastableB Loading…
1
cutlass-fa3 new mask interface cla signed fb-exported meta-exported
#5141 opened Nov 17, 2025 by arsatis Loading…
1
Bump setuptools from 75.1.0 to 78.1.1 in /fbgemm_gpu cla signed dependencies Pull requests that update a dependency file python Pull requests that update python code
#5139 opened Nov 16, 2025 by dependabot bot Loading…
Updated asmjit & adapted to its latest changes cla signed
#5137 opened Nov 15, 2025 by kobalicek Loading…
2
Slightly improve requantize_ AVX2 code performance cla signed fb-exported meta-exported
#5135 opened Nov 14, 2025 by mcfi Loading…
1
Vectorize requantize_ for Arm64 with NEON intrinsics cla signed fb-exported meta-exported
#5130 opened Nov 14, 2025 by mcfi Loading…
1
Allow specifiying the use of persistent kernel cla signed fb-exported meta-exported
#5129 opened Nov 14, 2025 by peiying779 Loading…
1
Extend raw_id_tracker to track ShardedManagedCollisionEmbeddingCollection cla signed fb-exported meta-exported
#5128 opened Nov 14, 2025 by FriedCosey Loading…
1
Enable arm64 convolution for fbgemm through the reference convolution APIs cla signed fb-exported meta-exported
#5126 opened Nov 13, 2025 by mcfi Loading…
1
minimize gpuAtomicAdd overhead in bounds_check_indices_kernel_v2 cla signed
#5124 opened Nov 13, 2025 by liligwu Loading…
1
Backward optimization for group_index_select_or_add_2d_kernel cla signed
#5123 opened Nov 13, 2025 by shbiswas834 Loading…
2
backward performance optimization for MI350 (#4925) cla signed fb-exported meta-exported module: rocm
#5121 opened Nov 12, 2025 by spcyppt Loading…
1
embedding forward optimization for rocm cla signed module: rocm
#5120 opened Nov 12, 2025 by JaxChen29 Loading…
add group_index_select_or_add_2d_kernel optimizations cla signed module: rocm
#5119 opened Nov 12, 2025 by shbiswas834 • Draft
1
Add NEON implementation of FloatOrHalfToFusedNBitRowwiseQuantizedSBHalf cla signed fb-exported meta-exported
#5115 opened Nov 11, 2025 by Nicoshev Loading…
2
Add support of 64 headDim cla signed fb-exported meta-exported
#5114 opened Nov 11, 2025 by Aya-ZIbra Loading…
2
upgrade cutlass cla signed fb-exported meta-exported
#5112 opened Nov 11, 2025 by jianyuh Loading…
2
accelerate permute_1D_data_kernel cla signed fb-exported meta-exported
#5110 opened Nov 10, 2025 by royren622 Loading…
1
Bm/cuda 13e cla signed
#5090 opened Nov 5, 2025 by q10 Loading…
1
Fix NAN for the prediction (#2096) cla signed fb-exported meta-exported
#5088 opened Nov 4, 2025 by quhang Loading…
2
Several kernel optimization from aiter team cla signed module: rocm
#5074 opened Oct 31, 2025 by Bernard-Liu • Draft
4
ProTip! Type g p on any issue or pull request to go back to the pull request listing page.