candle/candle-transformers/Cargo.toml

[package]
name = "candle-transformers"
version.workspace = true
edition.workspace = true
description.workspace = true
repository.workspace = true
keywords.workspace = true
categories.workspace = true
license.workspace = true
readme = "README.md"

[dependencies]
accelerate-src = { workspace = true, optional = true }
byteorder = { workspace = true }
candle = { workspace = true }
candle-flash-attn = { workspace = true, optional = true }
candle-nn = { workspace = true }
fancy-regex = { workspace = true }
intel-mkl-src = { workspace = true, optional = true }
num-traits = { workspace = true }
rand = { workspace = true }
rayon = { workspace = true }
serde = { workspace = true }
serde_json = { workspace = true }
serde_plain = { workspace = true }
tracing = { workspace = true }

[features]
default = []
accelerate = ["dep:accelerate-src", "candle/accelerate", "candle-nn/accelerate"]
cuda = ["candle/cuda", "candle-nn/cuda"]
flash-attn = ["cuda", "dep:candle-flash-attn"]
mkl = ["dep:intel-mkl-src", "candle/mkl", "candle-nn/mkl"]
metal = ["candle/metal", "candle-nn/metal"]
Sketch the candle-transformers crate. (#147) * Sketch the candle-transformers crate. * Format the empty files. 2023-07-12 20:49:31 +08:00			`[package]`
			`name = "candle-transformers"`
Update the repo location. (#305) 2023-08-02 18:12:18 +08:00			`version.workspace = true`
			`edition.workspace = true`
			`description.workspace = true`
			`repository.workspace = true`
			`keywords.workspace = true`
			`categories.workspace = true`
			`license.workspace = true`
Sketch the candle-transformers crate. (#147) * Sketch the candle-transformers crate. * Format the empty files. 2023-07-12 20:49:31 +08:00			`readme = "README.md"`

			`[dependencies]`
Support the Accelerate BLAS on macOS. (#325) * Add the accelerate feature. * Ffi tweaks. 2023-08-06 00:25:24 +08:00			`accelerate-src = { workspace = true, optional = true }`
Move the llama2-c model in transformers. (#1205) 2023-10-28 23:51:19 +08:00			`byteorder = { workspace = true }`
Simplifying our internal cargo dependencies. (#1529) 2024-01-07 19:04:14 +08:00			`candle = { workspace = true }`
			`candle-flash-attn = { workspace = true, optional = true }`
			`candle-nn = { workspace = true }`
Metavoice - first cut (#1717) * Add the metavoice transformer. * Sketch the speaker-encoder module. * Adding to the metavoice model. * Start adding the metavoice example. * Get some logits out. * Load the second stage model. * Get the second step to run. * Tweak the example. * Add encodec tilting. * Glue the different bits together. * Fix a shape issue. * Use a constant. * BPE tokenization. * Add a warning. 2024-03-03 01:50:01 +08:00			`fancy-regex = { workspace = true }`
Fix the mkl build. (#204) * Fix the mkl build. * Fix the build properly. 2023-07-20 02:41:11 +08:00			`intel-mkl-src = { workspace = true, optional = true }`
Move some models to candle-transformers so that it's easier to re-use. (#794) * Move some models to candle-transformers so that they can be shared. * Also move falcon. * Move Llama. * Move whisper (partial). 2023-09-10 16:40:27 +08:00			`num-traits = { workspace = true }`
Centralize the dependency versions and inherit them. (#177) 2023-07-16 14:47:17 +08:00			`rand = { workspace = true }`
Move more models to candle-transformers (#796) * Move dinov2. * Move efficientnet. * Move the quantized llama model. * Move segment-anything. 2023-09-10 17:20:18 +08:00			`rayon = { workspace = true }`
Move some models to candle-transformers so that it's easier to re-use. (#794) * Move some models to candle-transformers so that they can be shared. * Also move falcon. * Move Llama. * Move whisper (partial). 2023-09-10 16:40:27 +08:00			`serde = { workspace = true }`
			`serde_json = { workspace = true }`
Add support to UL2 model family (#1300) * Add support to UL2 model family * Update docs with UL2 * Create ActivationWithOptionalGating to avoid polluting activations * Also refactor quantized t5 * Remove useless conversion * Revert Activation::NewGelu name change * Remove useless return * Apply rustfmt and clippy recommendations * Reuse t5::ActivationWithOptionalGating in quantized version * (cosmetic change) use a match rather than ifs + avoid early returns. --------- Co-authored-by: Laurent <laurent.mazare@gmail.com> 2023-11-10 01:55:09 +08:00			`serde_plain = { workspace = true }`
Move some models to candle-transformers so that it's easier to re-use. (#794) * Move some models to candle-transformers so that they can be shared. * Also move falcon. * Move Llama. * Move whisper (partial). 2023-09-10 16:40:27 +08:00			`tracing = { workspace = true }`
Sketch the candle-transformers crate. (#147) * Sketch the candle-transformers crate. * Format the empty files. 2023-07-12 20:49:31 +08:00
			`[features]`
Removing cuda default. Seems very important for a lot of exploring users usually on laptop without GPUs. Adding more README instructions in a follow up. 2023-07-14 22:52:15 +08:00			`default = []`
Support the Accelerate BLAS on macOS. (#325) * Add the accelerate feature. * Ffi tweaks. 2023-08-06 00:25:24 +08:00			`accelerate = ["dep:accelerate-src", "candle/accelerate", "candle-nn/accelerate"]`
Sketch the candle-transformers crate. (#147) * Sketch the candle-transformers crate. * Format the empty files. 2023-07-12 20:49:31 +08:00			`cuda = ["candle/cuda", "candle-nn/cuda"]`
Add flash-attn support. (#912) * Add flash-attn support. * Add the use-flash-attn flag. * Re-enable flash-attn. 2023-09-20 21:07:55 +08:00			`flash-attn = ["cuda", "dep:candle-flash-attn"]`
Sketch the candle-transformers crate. (#147) * Sketch the candle-transformers crate. * Format the empty files. 2023-07-12 20:49:31 +08:00			`mkl = ["dep:intel-mkl-src", "candle/mkl", "candle-nn/mkl"]`
Lots of updates including some stack of command buffers. 2023-12-13 00:41:56 +08:00			`metal = ["candle/metal", "candle-nn/metal"]`