summaryrefslogtreecommitdiff
path: root/Cargo.toml
Commit message (Collapse)AuthorAgeFilesLines
...
* Re-organize the wasm examples (#231)Laurent Mazare2023-07-241-1/+2
| | | | | | | | | | | | | * Move the whisper example. * More renaming. * Add llama2 as a new wasm example. * Live generation. * More of the llama wasm example. * Formatting.
* Bump the hf-hub dependency to 0.1.3. (#206)Laurent Mazare2023-07-201-1/+1
|
* Fix the mkl build. (#204)Laurent Mazare2023-07-191-1/+1
| | | | | * Fix the mkl build. * Fix the build properly.
* Removing `candle-hub` internal to extract into `hf-hub` standalone.Nicolas Patry2023-07-191-9/+3
|
* Factorize the tokenizers version in the workspace cargo def. (#186)Laurent Mazare2023-07-181-1/+1
|
* Bert tracing (#184)Laurent Mazare2023-07-171-0/+3
| | | | | | | * Add some tracing to bert. * More tracing. * Add a flag for tracing.
* Gemm update (#183)Laurent Mazare2023-07-171-4/+5
| | | | | | | * Update the gemm dependency. * Update the comment too. * Pin the sha256 dependency.
* Centralize the dependency versions and inherit them. (#177)Laurent Mazare2023-07-161-0/+32
|
* Reenable pyo3 in the workspace list (#170)Laurent Mazare2023-07-141-1/+1
| | | | | * Enable pyo3 back. * Adapt the CI.
* Removing cuda default.Nicolas Patry2023-07-141-2/+4
| | | | | | | Seems very important for a lot of exploring users usually on laptop without GPUs. Adding more README instructions in a follow up.
* Wasm proof of concept. (#167)Laurent Mazare2023-07-141-0/+1
| | | | | | | | | | | * Wasm proof of concept. * Run whisper inference in the browser. * Some fixes. * Move the wasm example. * Change the tokenizer config.
* Use a rwlock for inner mutability. (#156)Laurent Mazare2023-07-131-1/+1
| | | | | * Use a rw-lock. * Make clippy happier.
* Tensor mutability (#154)Laurent Mazare2023-07-131-1/+1
| | | | | * Working towards tensor mutability. * Use a ref-cell to provide tensor mutability.
* Sketch the candle-transformers crate. (#147)Laurent Mazare2023-07-121-0/+1
| | | | | * Sketch the candle-transformers crate. * Format the empty files.
* Sketch the candle-nn crate. (#115)Laurent Mazare2023-07-101-0/+1
| | | | | | | * Sketch the candle-nn crate. * Tweak the cuda dependencies. * More cuda tweaks.
* Sketch the Falcon model. (#93)Laurent Mazare2023-07-061-0/+4
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | * Sketch the Falcon model. * Add more substance to the falcon example. * Falcon (wip). * Falcon (wip again). * Falcon inference. * Get the weights from the api and properly generate the model. * Use the proper model. * Fix the file/revision names. * Fix bias handling. * Recompute the rot embeddings. * Fix the input shape. * Add the release-with-debug profile. * Silly bugfix. * More bugfixes. * Stricter shape checking in matmul.
* Move llama in a cargo-examples directory.laurent2023-07-031-0/+1
|
* Very simple pyo3 bindings for candle.laurent2023-07-011-1/+2
|
* Revert the new profile.laurent2023-06-291-6/+0
|
* Add some KV cache to llama.laurent2023-06-291-1/+5
|
* [Tmp] Adding candle-hubNicolas Patry2023-06-271-0/+1
|
* Refactor the hierarchy.Nicolas Patry2023-06-271-33/+3
|
* More f16 and bf16 support.laurent2023-06-261-2/+2
|
* Start adding f16/bf16 support.laurent2023-06-261-1/+3
|
* Faster model weight loading.laurent2023-06-261-0/+1
|
* Remove the unecessary features.laurent2023-06-241-1/+1
|
* Read and write npy files.laurent2023-06-241-0/+1
|
* Moving to `gemm` and adding matmul backprop.Nicolas Patry2023-06-221-1/+1
| | | | - Tentative `T` operator.
* Fixing tokenizers dep.Nicolas Patry2023-06-221-1/+1
|
* Adding matmul?Nicolas Patry2023-06-221-0/+1
|
* Integrate the kernels bits.laurent2023-06-221-2/+8
|
* Abstract the gradient storage.laurent2023-06-211-0/+5
|
* Add some very basic tensor type.laurent2023-06-191-0/+21