Skip to content

Pull requests: pytorch/FBGEMM

New pull request New
289 Open 2,156 Closed
289 Open 2,156 Closed
Author
Filter by author
Label
Filter by label
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Milestones
Filter by milestone
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 memchecks to ssd split embeddings cache
cla signed fb-exported
#2589 opened May 13, 2024 by q10 Loading…
5
Fix undefined behavior
cla signed fb-exported
#2587 opened May 13, 2024 by MatzeB Loading…
3
FP32 Autovec Final Optimization
cla signed
#2586 opened May 13, 2024 by crystalrchen Loading…
1
FP8 tensorwise GEMM improvement
cla signed fb-exported
#2585 opened May 13, 2024 by jiawenliu64 Loading…
3
Add GenAI build only option
cla signed
#2584 opened May 13, 2024 by jianyuh • Draft
2
Re-organize TBE python files
cla signed fb-exported
#2583 opened May 11, 2024 by q10 Loading…
3
FP8 AMD Kernels
cla signed fb-exported
#2582 opened May 10, 2024 by jwfromm Loading…
3
Change rocksdb configs
cla signed fb-exported
#2581 opened May 10, 2024 by pranjalssh Loading…
3
Print periodic logs in SSD TBE benchmark
cla signed fb-exported
#2580 opened May 10, 2024 by pranjalssh Loading…
3
Set directory location is SSD TBE benchmarks
cla signed fb-exported
#2579 opened May 10, 2024 by pranjalssh Loading…
3
all_to_one cuda support non-2d inputs
cla signed fb-exported
#2575 opened May 9, 2024 by IvanKobzarev Loading…
5
Move group_index_select_dim0_gpu meta impl to python & remove CPU sync in GPU kernel
cla signed fb-exported
#2573 opened May 8, 2024 by williamwen42 Loading…
6
Add helper ops to support cache conflict misses
cla signed fb-exported
#2571 opened May 8, 2024 by sryap Loading…
6
wip
cla signed
#2570 opened May 7, 2024 by q10 Loading…
1
add max norm support to PARTIAL_ROWWISE_ADAM
cla signed fb-exported
#2567 opened May 7, 2024 by zainhuda Loading…
5
Implement multi-pass prefetch for memory efficiency
cla signed fb-exported
#2566 opened May 7, 2024 by levythu Loading…
3
Pyre Configurationless migration for] [batch:9/28]
cla signed fb-exported
#2557 opened May 3, 2024 by connernilsen Loading…
2
Fp8 updated
cla signed
#2550 opened Apr 30, 2024 by elopez0409 Loading…
1
Change the caller
cla signed
#2549 opened Apr 30, 2024 by jianyuh Loading…
1
Pyre Configurationless migration for] [batch:6/29]
cla signed
#2548 opened Apr 29, 2024 by connernilsen Loading…
1
Integrate triton row and blockwise fp8 gemm to llm inference.
cla signed fb-exported
#2547 opened Apr 29, 2024 by choutim Loading…
2
Add fp8 row/block-wise scaled GEMMs
cla signed
#2546 opened Apr 29, 2024 by choutim Loading…
1
Revert D56685840: Multisect successfully blamed "D56685840: [fbgemm] Change model transform fp8 linear op to fbgemm quantize ops" for one test failure
cla signed
#2545 opened Apr 29, 2024 by jianyuh Loading…
1
Refactor fbgemm / llama csrc code base
cla signed
#2544 opened Apr 29, 2024 by jianyuh Loading…
1
Make CowClipDefinition and CounterBasedRegularizationDefinition hashable
cla signed
#2539 opened Apr 27, 2024 by csmiler Loading…
1
ProTip! What’s not been updated in a month: updated:<2024-04-13.