Go
Home
Pricing
FAQ
Install
Home
Pricing
FAQ
Install
Login
via GitHub
FluxML/Flux.jl
Pull Requests
Commits
cl/dense-zero-batch
CarloLucibello-patch-1
CarloLucibello-patch-2
CarloLucibello-patch-3
CarloLucibello-patch-4
CarloLucibello-patch-5
CarloLucibello-patch-6
CarloLucibello-patch-7
CarloLucibello-patch-8
CarloLucibello-patch-9
CarloLucibello-patch-10
CarloLucibello-patch-11
CarloLucibello-patch-12
bc/logexpfunctions
bc/norm-type-stability
bc/vchain-rrule
cl/agents
cl/allocator
cl/autocast
cl/autocast-wrapper
cl/auxmoon
cl/batchnorm-single-sample-error
cl/bf16-mixed-precision-norm
cl/bf16
cl/cachealloc
cl/caching-allocator
cl/component
cl/conv-padding-modes
cl/cuda3
cl/cudadocs
cl/cudaext
cl/dense-zero-batch
cl/depre
cl/device
cl/devices
cl/doc4
cl/docs
cl/docs3
cl/docsattention
cl/downstream
cl/enz2
cl/enz4
cl/enzyme2
cl/expand
cl/ext
cl/fix-check-equal-leaves
cl/fixback
cl/fixci
cl/fixcu
cl/fixdocs
cl/fixenz
cl/fp
cl/funct
cl/funct2
cl/gpu
cl/grad
cl/id
cl/load
cl/los
cl/lstm
cl/lstm2
cl/maintain
cl/metal2
cl/misc2
cl/mixed
cl/mldata
cl/moon
cl/moon2
cl/nll
cl/norm-nnlib
cl/pad_idx
cl/params
cl/pir
cl/public
cl/react
cl/reactant
cl/reactant-adam-benchmark
cl/reactant-aux-single-forward
cl/reactant-benchmark
cl/reactant-docs-example
cl/reactant-train
cl/rec-doc
cl/recur
cl/resnet-tinyimagenet
cl/rnn
cl/rnn2
cl/sched
cl/state
cl/tests
cl/testsfix
cl/train
cl/train-adaptive-gpu-memory
cl/train-step
cl/train-step-aux
cl/trainstep
cl/trainstep-adtype-resolution
cl/unbreak
cl/update-news
cl/v0.15
cl/v16
cl/warn
cl/withgradient-aux
cl-docs
compathelper/new_version/2023-05-02-00-16-19-461-00167845480
compathelper/new_version/2023-06-15-00-24-31-667-04255233286
compathelper/new_version/2023-10-29-00-17-44-206-00447538703
compathelper/new_version/2024-04-18-00-16-09-894-00366782878
compathelper/new_version/2024-04-18-00-16-14-958-02693456771
compathelper/new_version/2024-06-16-00-18-52-757-03516511688
compathelper/new_version/2024-06-25-00-17-09-712-01861810404
compathelper/new_version/2024-08-09-00-18-29-713-03254374619
compathelper/new_version/2024-11-05-00-20-58-633-02374792264
compathelper/new_version/2024-11-08-00-20-35-115-00680202294
compathelper/new_version/2025-01-08-00-20-36-499-01334285076
compathelper/new_version/2026-01-27-00-28-27-946-02539025090
compathelper/new_version/2026-04-11-00-34-47-548-02086536477
compathelper/new_version/2026-04-11-00-34-52-073-01340497663
copilot/activate-enzyme-tests-julia-1-12
dependabot/github_actions/actions/checkout-7
dependabot/github_actions/julia-actions/setup-julia-3
dg/optimisers
dg/step
fix/fluxmpiextension_cuda_optional
gh-pages
gpu_docs
master
mcabbott-patch-1
ox/perfdocglobalmodel
release-0.14
rnn-hotfix
vs/tagbot
Fix Dense with a zero-sized batch dimension (#2407)
CarloLucibello
committed
57 days ago
b3be2f63
fix stack overflow when passing empty struct (#2670)
hardikxk
committed
58 days ago
Verified
18f475ef
BatchNorm: error on a single value per channel in training (fixes #1992) (#2716)
CarloLucibello
committed
60 days ago
Verified
3f2f828b
Bump version from 0.16.10 to 0.16.11
CarloLucibello
committed
62 days ago
Verified
443ed1bc
Resolve AD backend once for `train!`/`trainstep!`; honour explicit `adtype` on Reactant (#2714)
CarloLucibello
committed
62 days ago
Verified
6af22a1e
Reactant docs guide + `trainstep!` in the ResNet example & benchmark (#2713)
CarloLucibello
committed
62 days ago
Verified
c7b0217c
Reactant trainstep!: single-forward aux, host-side outputs, cache warning (#2712)
CarloLucibello
committed
62 days ago
Verified
cea47b23
train_step! -> trainstep!
CarloLucibello
committed
63 days ago
067e83d5
cleanup
CarloLucibello
committed
63 days ago
2dda675e
Support auxiliary loss outputs in train_step! and train! (#2711)
CarloLucibello
committed
63 days ago
Verified
c234ff91
add padding_idx to Embedding (#2708)
CarloLucibello
committed
63 days ago
Verified
0170e9e2
Support auxiliary outputs in Enzyme `withgradient` (#2710)
CarloLucibello
committed
63 days ago
Verified
0f7d6f33
Add public `train_step!`, build `train!` on top of it (#2709)
CarloLucibello
committed
63 days ago
Verified
d744107a
Compile `train!` on Reactant devices (#2707)
CarloLucibello
committed
64 days ago
Verified
2f03a1b0
perf/reactant: benchmark Adam (Optimisers 0.4.8), fix BatchNorm loss-probe artifact (#2706)
CarloLucibello
committed
64 days ago
Verified
f5c123d8
cleanup repo (#2705)
CarloLucibello
committed
64 days ago
Verified
10ee4907
Add Zygote-vs-Reactant training benchmark (perf/reactant) (#2704)
CarloLucibello
committed
64 days ago
Verified
0267f613
Mixed-precision f16/bf16 for BatchNorm/InstanceNorm/GroupNorm (#2700)
CarloLucibello
committed
65 days ago
Verified
740f744a
Delegate normalization layers to NNlib functional operators (#2701)
CarloLucibello
committed
65 days ago
Verified
ee4ec090
Add bf16 precision helper (#2698)
CarloLucibello
committed
65 days ago
Verified
1e78c106
Overhaul NEWS.md and document changelog upkeep (#2699)
CarloLucibello
committed
65 days ago
Verified
7078bc8f
Add a ResNet-18 / Tiny-ImageNet-200 example (#2696)
CarloLucibello
committed
66 days ago
Verified
bad1d314
Adaptive GPU memory management in train! (#2697)
CarloLucibello
committed
66 days ago
Verified
ca6e8c06
Add option to disable the caching allocator in train! (#2695)
CarloLucibello
committed
67 days ago
Verified
f4a72bcd
Fix check_equal_leaves so gradient comparisons actually run (#2693)
CarloLucibello
committed
78 days ago
Verified
780af631
unbreak some metal tests (#2692)
CarloLucibello
committed
79 days ago
Verified
d618f1ff
docs: fix typos and trim trailing whitespace (#2691)
jeis4wpi
committed
79 days ago
Verified
d099c22c
Update default for FLUX_TEST_ENZYME (#2690)
wsmoses
committed
86 days ago
Verified
38e189dd
Bump dorny/paths-filter from 4.0.1 to 4.0.2 (#2689)
dependabot[bot]
committed
92 days ago
Verified
4d504e09
unbreak enzyme tests (#2688)
CarloLucibello
committed
105 days ago
Verified
57e29baf
Older