Skip to content

Pull requests: pytorch/FBGEMM

New pull request New
453 Open 3,510 Closed
453 Open 3,510 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

optimization of perKVhead quantization cla signed fb-exported
#4161 opened May 20, 2025 by Aya-ZIbra Loading…
4
support filling partial rows from backend cla signed fb-exported
#4158 opened May 20, 2025 by duduyi2013 Loading…
2
Leverage fuse kernel in inference workload (#1237) cla signed fb-exported
#4157 opened May 20, 2025 by ycui1984 Loading…
3
Jemalloc Mempool and Adaptation for CPU HASHTABLE cla signed
#4154 opened May 20, 2025 by ArronHZG Loading…
2
Add more parameter specializations for autovec TBE kernels cla signed fb-exported
#4153 opened May 20, 2025 by excelle08 Loading…
3
improve read/write performance by 100% cla signed fb-exported
#4150 opened May 19, 2025 by steven1327 Loading…
2
Make iter persistent for AdagradW cla signed fb-exported
#4147 opened May 17, 2025 by minhua-chen Loading…
5
support get state dict and apply state dict cla signed fb-exported
#4145 opened May 17, 2025 by emlin Loading…
7
reduce UT emb table size cla signed fb-exported
#4136 opened May 16, 2025 by duduyi2013 Loading…
2
Simplify grouped gemm output allocations cla signed fb-exported
#4134 opened May 16, 2025 by jwfromm Loading…
2
Update the rowwise adagrad optimizer to leverage optimizer state offloading, v3 cla signed fb-exported
#4133 opened May 15, 2025 by q10 Loading…
7
Add TBE data configuration reporter to TBE forward" cla signed fb-exported
#4130 opened May 15, 2025 by gchalump Loading…
12
Remove fbgemm autovec cla signed fb-exported
#4123 opened May 14, 2025 by gchalump Loading…
5
Trim constexpr from isA to improve Windows clang-cl support. cla signed
#4119 opened May 13, 2025 by ScottTodd Loading…
2
Fix computation of maxIndex in EEG cla signed fb-exported
#4112 opened May 12, 2025 by q10 Loading…
2
Fix OSS GenAI cla signed fb-exported
#4105 opened May 9, 2025 by spcyppt Loading…
6
Add tensor_stream unit test cla signed fb-exported
#4099 opened May 8, 2025 by chouxi Loading…
8
Replace C10_CUDA_KERNEL_LAUNCH_CHECK() in the KernelLauncher cla signed fb-exported
#4097 opened May 8, 2025 by q10 Loading…
2
Do FP8 rowwise bias addition in higher precision cla signed fb-exported
#4095 opened May 8, 2025 by jwfromm Loading…
3
Add HSTU in fbgemm_gpu/experimental/ cla signed
#4090 opened May 7, 2025 by jiayus-nvidia Loading…
5
Use bounds_check_indices v2 on ROCm ciflow/rocm cla signed fb-exported module: rocm
#4085 opened May 6, 2025 by sryap Loading…
3
Change GenAI OSS runner to fix OOM cla signed fb-exported
#4082 opened May 6, 2025 by spcyppt Loading…
3
Migrate TBE backward kernels to FBGEMM_LAUNCH_KERNEL cla signed fb-exported
#4076 opened May 5, 2025 by q10 Loading…
2
Back out "Simplify weight row cache load and evict routines" cla signed fb-exported
#4064 opened May 1, 2025 by q10 Loading…
2
iRoPE (-p > 8192) cla signed fb-exported
#4063 opened May 1, 2025 by y-sq Loading…
3
ProTip! Updated in the last three days: updated:>2025-05-18.