8000 Tags · KristianHolme/Lux.jl · GitHub
[go: up one dir, main page]
More Web Proxy on the site http://driver.im/
Skip to content

Tags: KristianHolme/Lux.jl

Tags

LuxLib-v1.7.3

Toggle LuxLib-v1.7.3's commit message
[Diff since LuxLib-v1.7.2](LuxDL/Lux.jl@LuxLib-v1.7.2...LuxLib-v1.7.3)

**Merged pull requests:**
- fix: remove Optimisers.jl patch (LuxDL#1247) (@avik-pal)
- show debug instead of warning if cant cuBLAS mult (LuxDL#1280) (@ExpandingMan)
- chore: bump crate-ci/typos from 1.30.2 to 1.31.0 (LuxDL#1281) (@dependabot[bot])
- chore: remove debug functionalities of reactant (LuxDL#1285) (@avik-pal)
- fix: add a ReactantOptimisers wrapper (LuxDL#1288) (@avik-pal)
- chore: bump crate-ci/typos from 1.31.0 to 1.31.1 (LuxDL#1297) (@dependabot[bot])
- ci: use JuliaFormatter v1 (LuxDL#1299) (@avik-pal)
- ci: multiple ci fixes (LuxDL#1301) (@avik-pal)
- CompatHelper: bump compat for JET to 0.10 for package LuxTestUtils, (keep existing compat) (LuxDL#1302) (@github-actions[bot])
- fix: new reactant version (LuxDL#1303) (@avik-pal)
- fix: update Reactant training (LuxDL#1304) (@avik-pal)
- fix: chain rules for recurrence tuple inputs (LuxDL#1306) (@avik-pal)
- feat: fix return (LuxDL#1307) (@avik-pal)
- fix: try increasing the samples in CI (LuxDL#1309) (@avik-pal)
- fix: restrict dispatch types for cublaslt (LuxDL#1311) (@avik-pal)

**Closed issues:**
- Optimisers.jl patch for Reactant Support (LuxDL#1146)
- Convolutional VAE for MNIST using Reactant failed to produce right results (LuxDL#1274)
- GPU Inefficiency in Gradient Computation with Custom Recurrence (LuxDL#1284)
- PINN2DPDE broke in the latest Optimisers Patch removal (LuxDL#1286)
- Duplicating Scalars for Optimisers prevents CSE (LuxDL#1289)
- Reactant 0.2.61 produces incorrect gradients (LuxDL#1292)
- missing or incorrect `ProjectTo` method breaks `Recurrence` with Zygote (LuxDL#1305)
- dense operations fail on views on nvidia due to missing method (LuxDL#1308)

v1.12.4

Toggle v1.12.4's commit message
[Diff since v1.12.3](LuxDL/Lux.jl@v1.12.3...v1.12.4)

**Merged pull requests:**
- feat: fix return (LuxDL#1307) (@avik-pal)

v1.12.3

Toggle v1.12.3's commit message
[Diff since v1.12.2](LuxDL/Lux.jl@v1.12.2...v1.12.3)

**Merged pull requests:**
- fix: update Reactant training (LuxDL#1304) (@avik-pal)
- fix: chain rules for recurrence tuple inputs (LuxDL#1306) (@avik-pal)

**Closed issues:**
- Duplicating Scalars for Optimisers prevents CSE (LuxDL#1289)
- missing or incorrect `ProjectTo` method breaks `Recurrence` with Zygote (LuxDL#1305)

v1.12.2

Toggle v1.12.2's commit message
[Diff since v1.12.1](LuxDL/Lux.jl@v1.12.1...v1.12.2)

**Merged pull requests:**
- chore: bump crate-ci/typos from 1.31.0 to 1.31.1 (LuxDL#1297) (@dependabot[bot])
- ci: use JuliaFormatter v1 (LuxDL#1299) (@avik-pal)
- ci: multiple ci fixes (LuxDL#1301) (@avik-pal)
- CompatHelper: bump compat for JET to 0.10 for package LuxTestUtils, (keep existing compat) (LuxDL#1302) (@github-actions[bot])
- fix: new reactant version (LuxDL#1303) (@avik-pal)

**Closed issues:**
- Reactant 0.2.61 produces incorrect gradients (LuxDL#1292)

v1.12.1

Toggle v1.12.1's commit message
[Diff since v1.12.0](LuxDL/Lux.jl@v1.12.0...v1.12.1)

**Merged pull requests:**
- fix: add a ReactantOptimisers wrapper (LuxDL#1288) (@avik-pal)

**Closed issues:**
- PINN2DPDE broke in the latest Optimisers Patch removal (LuxDL#1286)

v1.12.0

Toggle v1.12.0's commit message
[Diff since v1.11.2](LuxDL/Lux.jl@v1.11.2...v1.12.0)

**Merged pull requests:**
- fix: remove Optimisers.jl patch (LuxDL#1247) (@avik-pal)
- show debug instead of warning if cant cuBLAS mult (LuxDL#1280) (@ExpandingMan)
- chore: bump crate-ci/typos from 1.30.2 to 1.31.0 (LuxDL#1281) (@dependabot[bot])
- chore: remove debug functionalities of reactant (LuxDL#1285) (@avik-pal)

**Closed issues:**
- Optimisers.jl patch for Reactant Support (LuxDL#1146)

v1.11.2

Toggle v1.11.2's commit message
[Diff since v1.11.1](LuxDL/Lux.jl@v1.11.1...v1.11.2)

**Merged pull requests:**
- test: fix tests (LuxDL#1278) (@avik-pal)
- fix: try fixing broken tests (LuxDL#1279) (@avik-pal)

LuxLib-v1.7.2

Toggle LuxLib-v1.7.2's commit message
[Diff since LuxLib-v1.7.1](LuxDL/Lux.jl@LuxLib-v1.7.1...LuxLib-v1.7.2)

**Merged pull requests:**
- test: fix tests (LuxDL#1278) (@avik-pal)
- fix: try fixing broken tests (LuxDL#1279) (@avik-pal)

v1.11.1

Toggle v1.11.1's commit message
[Diff since v1.11.0](LuxDL/Lux.jl@v1.11.0...v1.11.1)

**Merged pull requests:**
- chore: bump forwarddiff to 1.0 (LuxDL#1277) (@avik-pal)

v1.11.0

Toggle v1.11.0's commit message
[Diff since v1.10.1](LuxDL/Lux.jl@v1.10.1...v1.11.0)

**Merged pull requests:**
- docs: refer to the Turing docs for BayesianNN (LuxDL#1272) (@github-actions[bot])
- feat: support for ForwardDiff training (LuxDL#1273) (@hstrey)
0