summaryrefslogtreecommitdiff
path: root/candle-wasm-examples
Commit message (Collapse)AuthorAgeFilesLines
* Add Stable Diffusion 3 Example (#2558)Czxck0012024-10-131-1/+1
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | * Add stable diffusion 3 example Add get_qkv_linear to handle different dimensionality in linears Add stable diffusion 3 example Add use_quant_conv and use_post_quant_conv for vae in stable diffusion adapt existing AutoEncoderKLConfig to the change add forward_until_encoder_layer to ClipTextTransformer rename sd3 config to sd3_medium in mmdit; minor clean-up Enable flash-attn for mmdit impl when the feature is enabled. Add sd3 example codebase add document crediting references pass the cargo fmt test pass the clippy test * fix typos * expose cfg_scale and time_shift as options * Replace the sample image with JPG version. Change image output format accordingly. * make meaningful error messages * remove the tail-end assignment in sd3_vae_vb_rename * remove the CUDA requirement * use default_value in clap args * add use_flash_attn to turn on/off flash-attn for MMDiT at runtime * resolve clippy errors and warnings * use default_value_t * Pin the web-sys dependency. * Clippy fix. --------- Co-authored-by: Laurent <laurent.mazare@gmail.com>
* Clippy fixes for 1.81.0. (#2461)Laurent Mazare2024-09-052-2/+2
| | | | | * Clippy fixes for 1.81.0. * Another fix.
* Clippy fixes. (#2415)Laurent Mazare2024-08-146-23/+18
| | | | | * Clippy fixes. * Bump the web_sys required version.
* bert attention mask (#1934)Zheng Li2024-08-011-1/+11
| | | | | | | | | | | | | | | * bert attention mask * Allow for using None as a mask. * Revert part of the changes so that the proper default mask applies. * Cosmetic change. * Another cosmetic tweak. --------- Co-authored-by: Laurent <laurent.mazare@gmail.com>
* change DTypes (fixes #2355) (#2363)Jacob Marshall2024-07-281-2/+2
|
* onnx: fix pad, unsqueeze (#2317)shua2024-07-234-5/+5
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | * onnx: fix pad, unsqueeze both implementations have off-by-one errors: - Pad 'reflect' cycle for eg `dim==3` is `[0,1,2,1]` which has length of 4 (or `dim*2 - 2`) not 5 (current code `dim*2 - 1`) - Unsqueeze(-1) for tensor with `dim==3` should be 3 (ie `dim+index+1`) not 2 (ie currently `dim+index`) in addition, Pad is incorrectly calculating the starting padding. If we want to pad out 2 elements to the start, and we have this cycle of indices of length 6, then we should skip 4 elements, but currently we skip 2. A more visual representation of what's going on is below: ``` pad_start: 2 data: [a,b,c,d] indices: [0, 1, 2, 3, 2, 1, 0, 1, 2, 3, 2, 1, 0, ..] // zigzag between 0..4 actual: skip [ c d| c b a b] expected: ~ skip ~ [ c b| a b c d] ``` The values between `[` and `|` are padding and the values between `|` and `]` in the example should match the original data being padded. * Fix clippy lints. --------- Co-authored-by: Laurent <laurent.mazare@gmail.com>
* Remove the deprecated wav crate in favor of hound. (#2202)Laurent Mazare2024-05-212-9/+12
|
* Bump the version number to 0.5.1. (#2155)Laurent Mazare2024-05-031-21/+0
| | | | | | | * Bump the version number to 0.5.1. * Fix clippy lints for 1.78. * More clippy fixes.
* Moondream WASM (#1999)Radamés Ajna2024-04-038-0/+1128
| | | | | | | | | | | | | * moondream wasm wip * examples, more * fix eos token check * README * cleanip * cleanup, clippy
* Detach the tensors on batch-norm eval. (#1702)Laurent Mazare2024-02-131-1/+2
| | | | | | | | | | | | | * Detach the tensors on batch-norm eval. * Fix pyo3 bindings. * Black tweak. * Formatting. * Also update the pyo3-onnx formatting. * Apply black.
* Quantized GGUF style (#1523)Nicolas Patry2024-01-174-7/+11
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | * Metal quantized modifications proposal. - Add a device param, wherever needed. - Create new QMetal storage thing that implements QuantizedType. - Update everywhere needed. Fix Python. Fixing examples. Fix: fmt + clippy + stub. Moving everything around. Only missing the actual implems. Fixing everything + adding dequantized kernels. More work. Fixing matmul. Fmt + Clippy Some clippy fixes. Working state. Q2K Metal -> Bugged (also present in GGML). Q4K CPU -> Bugged (present previously, new test catch it). Q5K CPU -> Bugged (present previously). Q8_1 Both -> Never really implemented it seems Q8K metal -> Never implemented in metal Fixing Q2K bug (present in ggml). * Cleanup. * Fix the rebase. * Removing the fences speeds everything up and *is* correct this time... * Cleanup the fence. * After rebase. * Bad code removal. * Rebase after phi2 merge + fix replit default to CPU. * Making the CI happy. * More happy tests. --------- Co-authored-by: Nicolas Patry <nicolas@Nicolass-MacBook-Pro.local>
* Update gloo requirement from 0.8 to 0.11 (#1558)dependabot[bot]2024-01-105-5/+5
| | | | | | | | | | | | | | | Updates the requirements on [gloo](https://github.com/rustwasm/gloo) to permit the latest version. - [Release notes](https://github.com/rustwasm/gloo/releases) - [Changelog](https://github.com/rustwasm/gloo/blob/master/CHANGELOG.md) - [Commits](https://github.com/rustwasm/gloo/commits) --- updated-dependencies: - dependency-name: gloo dependency-type: direct:production ... Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
* Simplifying our internal cargo dependencies. (#1529)Nicolas Patry2024-01-078-23/+23
|
* Do not implement Module for BatchNorm. (#1513)Laurent Mazare2024-01-011-2/+1
|
* Fix lints for clippy 1.75. (#1494)Laurent Mazare2023-12-283-21/+19
|
* Bump the crate version to 0.3.3. (#1490)Laurent Mazare2023-12-288-23/+23
|
* Bump the crate version to 0.3.2. (#1452)Laurent Mazare2023-12-178-23/+23
|
* Fix a couple typos (#1451)Laurent Mazare2023-12-176-6/+6
| | | | | * Mixtral quantized instruct. * Fix a couple typos.
* Phi 2 wasm (#1432)Radamés Ajna2023-12-143-26/+102
| | | | | | | | | * add phi 2.0 quantized model wasm * cols * spell * bug
* Use the whisper-v3 tokenizer now that it has been added. (#1337)Laurent Mazare2023-11-161-1/+7
| | | | | * Use the whisper-v3 tokenizer now that it has been added. * Use the appropriate nospeech token.
* fix: address clippy 0.1.74 issues (#1336)drbh2023-11-161-2/+1
| | | | - clippy::needless-borrows-for-generic-args - clippy::reserve-after-initialization
* Update for 0.3.1. (#1324)Laurent Mazare2023-11-118-23/+23
|
* Preliminary support for whisper v3. (#1294)Laurent Mazare2023-11-082-3/+5
| | | | | * Preliminary support for whisper v3. * Add the missing files.
* add distil-whisper link (#1261)Radamés Ajna2023-11-031-35/+49
|
* llama2-c wasm fix.Laurent2023-11-021-1/+3
|
* Minor cleanup (#1194)Laurent Mazare2023-10-271-17/+3
| | | | | * Add some missing backtraces. * Small cleanup.
* [Wasm] BLIP Example (#1183)Radamés Ajna2023-10-268-0/+777
| | | | | | | | | | | * blip wasm start * fix dependency issue, move token stream here * vanilla js worker * roll back vscode * spell
* [Wasm] Add puffin phi model to wasm (#1166)Radamés Ajna2023-10-253-38/+204
| | | | | | | * load config from file, add puffin phi links * format * add prompt examples
* Remove some unusued bits. (#1067)Laurent Mazare2023-10-092-2/+0
|
* feat: [SAM] able to download the result as png (#1035)lichin-lin2023-10-051-0/+60
| | | | | * feat: able to download the result as png * feat: update function and wording
* Quant t5: Add coedit model to wasm demo and readme (#1031)Juarez Bochi2023-10-042-4/+44
|
* Whisper quantized wasm (#1028)Radamés Ajna2023-10-0412-596/+539
| | | | | | | | | | | | | * [Whisper] Update to use quantized model * [whisper] add language detection * [whisper] change assets location * [whisper] adapt js example with quantized models * [whisper] better task parsing * [whisper] minor fixes
* [SAM] Add undo button and background point mode (#1020)Radamés Ajna2023-10-021-61/+165
| | | | | | | | | * [SAM] Add undo button and background point mode * [SAM] remove pts on near clicks * [SAM] check shiftKey toggle point mode * [SAM] clear points when clearing image
* [segment-anything] add multi point logic for demo site (#1002)lichin-lin2023-10-013-14/+29
| | | | | * [segment-anything] add multi point logic for demo site * [segment-anything] remove libs and update functions
* Bump the version to 0.3.0. (#1014)Laurent Mazare2023-10-017-19/+19
| | | | | * Bump the version to 0.3.0. * Changelog update.
* Add negative prompts to segment-anything. (#1000)Laurent Mazare2023-09-301-1/+1
|
* Phi 1.5 wasm module (#966)Radamés Ajna2023-09-277-0/+725
| | | | | | | | | | | | | | | | | | | | | | | | | | | * add phi wasm module * replace input with textarea * trim input prompt * stop on <|endoftext|> * formatting * clean up * add blurb, and syntax highlighting * add phi-v1.5 wasm * add note * hide Options on details * add first token to generated text * whitespaces for new line * fix: abort -> aborted
* fix firstToken, minor ui changes (#971)Radamés Ajna2023-09-272-100/+101
|
* fix rep penalty min value (#963)Radamés Ajna2023-09-262-2/+2
|
* [segment-anything] Support multi-point as the prompt input (#945)GeauxEric2023-09-251-1/+1
| | | | | | | | | | | | | | * [sam] Support multi-point prompts * [segment-anything] Pass points by reference * [segment-anything] Update example code and image * Fix clippy lint. --------- Co-authored-by: Yun Ding <yunding@nvidia.com> Co-authored-by: laurent <laurent.mazare@gmail.com>
* Depreate the VarBuilder::from_safetensors function. (#951)Laurent Mazare2023-09-241-3/+2
|
* Pass directly the buffer ownership. (#949)Laurent Mazare2023-09-245-18/+12
|
* smaller t5 models quantized (#934)Radamés Ajna2023-09-221-2/+2
|
* T5 Wasm (#918)Radamés Ajna2023-09-2210-0/+1115
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | * init t5 wasm model * split workers for each model * clean up * add some ui * readme * index * typo * remove cache param, clear_kv_cache * add max_length as param * add model tasks option to ui * add method to load quantized gguf from buffer * Add quantized wasm module * add quantized models to UI, dynamic import wasms * link to quantized * fix copy * fix ModelEncoder * fix README.md
* BERT Wasm (#902)Radamés Ajna2023-09-198-0/+717
| | | | | | | | | | | | | * implement wasm module * add example to workspace * add UI explore semantic similiarity * change status messages * formatting * minor changes
* Bump the crate versions to v0.2.3. (#886)Laurent Mazare2023-09-184-10/+10
| | | | | * Bump the crate version. * Also update the python bindings.
* Fix typos in SAM WASM example (#884)Aaron Sun2023-09-181-2/+2
|
* Update README + SAM (#866)Radamés Ajna2023-09-163-5/+4
| | | | | * use serde-wasm-bindgen, faster serialization * update readme with demos
* Add SAM UI Demo (#854)Radamés Ajna2023-09-154-2/+609
| | | | | | | | | | | | | * fix tensor flattening * send image data back * sam ui worker example * SAM example * resize container * no need for this
* minor UI fixes (#856)Radamés Ajna2023-09-153-11/+27
| | | | | | | * fixes * remove listener * remove event listener
generated by cgit v1.2.3 (git 2.39.1) at 2025-04-04 02:54:07 +0000