104e196d46
Phi 2 wasm ( #1432 )
...
* add phi 2.0 quantized model wasm
* cols
* spell
* bug
2023-12-14 06:04:17 -06:00
5e33c85c8f
Quantized version for phi-v2. ( #1430 )
...
* Quantized version for phi-v2.
* More quantized support.
2023-12-13 21:16:34 -06:00
2b3a018be7
Support for phi-2. ( #1429 )
...
* Support for phi-2.
* Use the v2 naming scheme.
2023-12-13 20:59:29 -06:00
4cb443d00a
Fix the logsumexp test. ( #1426 )
2023-12-12 10:56:11 -06:00
77252ffb82
Add logsumexp function ( #1424 )
2023-12-12 10:32:17 -06:00
18eb87f25f
Upsample grad ( #1420 )
...
* encode size of upsample in enum
* working convolution method for limited 2d kernels
* add test for sf 3 interpolation
* add higher dimensional tests, fix to work with multichannel input
* Remove commented out line.
---------
Co-authored-by: Laurent <laurent.mazare@gmail.com >
2023-12-10 08:43:24 +01:00
9bd94c1ffa
Speed up bert with approx gelu ( #1410 )
2023-12-06 17:46:37 +01:00
236b820e28
Another prelu bugfix. ( #1407 )
2023-12-06 09:54:41 +01:00
2648e797c2
Use the proper broadcasting for prelu. ( #1406 )
2023-12-05 07:09:31 +01:00
b5c283e86f
Add the prelu layer. ( #1402 )
2023-12-03 16:06:09 +00:00
8418154ee0
Add nvcc ccbin support to examples ( #1401 )
2023-12-03 16:01:16 +00:00
99b7273b03
Add compute cap env support to examples ( #1400 )
2023-12-03 16:00:24 +00:00
16161145ae
Add the leo models to the quantized examples. ( #1398 )
2023-12-03 12:30:41 +00:00
0738df5290
Add more mentions to SDXL Turbo in the readme. ( #1397 )
2023-12-03 10:41:21 +00:00
37bf1ed012
Stable Diffusion Turbo Support ( #1395 )
...
* Add support for SD Turbo
* Set Leading as default in euler_ancestral discrete
* Use the appropriate default values for n_steps and guidance_scale.
---------
Co-authored-by: Laurent <laurent.mazare@gmail.com >
2023-12-03 08:37:10 +01:00
dd40edfe73
Add Euler Ancestral Discrete Scheduler ( #1390 )
...
* Add Euler Ancestral Discrete Scheduler
* Fix a bug of init_noise_sigma generation
* minor fixes
* use partition_point instead of custom bsearch
* Fix some clippy lints.
---------
Co-authored-by: laurent <laurent.mazare@gmail.com >
2023-12-02 19:59:23 +00:00
5aa1a65dab
Add quantized Starling, fix open-chat prompt ( #1393 )
...
* Add quantized Starling, fix open-chat prompt
* Fix open-chat and starling prompts
2023-12-02 16:47:19 +00:00
7c3cfd1086
Use the llama weight names for the Yi example. ( #1381 )
2023-11-27 20:42:52 +00:00
e2eb6590ed
Merge pull request #1323 from huggingface/metal3
...
Adding the test scaffolding.
2023-11-27 13:06:01 +01:00
481c45d78d
Add a basic implementation for slice-assign. ( #1377 )
2023-11-26 17:31:22 +00:00
14a2bdc062
Small tweak: remove the macro usage for the range indexing trait. ( #1376 )
2023-11-26 16:30:59 +00:00
bfa7c8fc01
Implement the module trait directly for QMatMul. ( #1372 )
2023-11-25 10:09:45 +00:00
762e996ce6
Distibert ( #1366 )
...
* add bce with logit loss
* add bce with logit loss
* remove imports
* fix tiny bug
* add test documentation and refactor function
* fix test cases and formatting
* distilbet files
* Apply various cleanups.
* More cleanups.
* More polish.
---------
Co-authored-by: laurent <laurent.mazare@gmail.com >
2023-11-24 15:09:14 +00:00
ca19a9af62
Fix linspace implementation ( #1358 )
...
* Fix linspace implementation
`steps` should be strictly greater than 1 to make it consistent with the context.
* Handle steps == 0 and steps == 1.
* Fix rustfmt.
---------
Co-authored-by: laurent <laurent.mazare@gmail.com >
2023-11-23 07:35:13 +00:00
ec23427d60
Ensure to copy data to cpu before iterating. ( #1360 )
2023-11-23 07:24:25 +00:00
f83e14f68d
Add candle-lora transformers to readme? ( #1356 )
...
* Demonstrate lora transformers in readme
* Shorten readme
2023-11-21 17:54:24 +00:00
c7e613ab5e
Update the readme. ( #1354 )
2023-11-21 09:38:27 +00:00
8f63f68289
Fix the kalosm link ( #1353 )
2023-11-21 06:18:14 +01:00
1edc3ddf24
Allowing feature metal to compile.
2023-11-20 20:17:16 +01:00
b380657bfe
Merge pull request #1309 from huggingface/metal2
...
Adding the actual backend
2023-11-20 17:24:01 +01:00
60f624a902
Moving tests around.
2023-11-20 16:17:19 +01:00
8d6c6de8e0
Missing new test.
2023-11-20 14:38:35 +01:00
7ec345c2eb
Adding the test scaffolding.
2023-11-20 14:38:35 +01:00
671fc29b36
Fmt.
2023-11-20 14:38:20 +01:00
dc64adb8e4
Fixing cos_f16 test.
2023-11-20 14:17:07 +01:00
c66e5d4716
Fix comments.
2023-11-20 14:13:44 +01:00
bd3b243725
Update candle-metal-kernels/Cargo.toml
2023-11-20 14:12:57 +01:00
2813fb5dbc
Cleanup fixed a few ops removed debugging scaffolding.
2023-11-20 14:12:57 +01:00
7cfffcac10
Debugging rope.
2023-11-20 14:12:57 +01:00
38de52bc4b
Fixed matmul (display still broken without casting back to CPU first? )
2023-11-20 14:12:57 +01:00
d46670f7c0
Tmp state.
2023-11-20 14:12:57 +01:00
f710fab02e
Fixing the kernels + launches to make them faster.
...
Cool work by @ivarflakstad
Co-authored-by: Ivar Flakstad <69173633+ivarflakstad@users.noreply.github.com >
2023-11-20 14:12:57 +01:00
f82bf2d915
Adding indexing.
...
Co-authored-by: Ivar Flakstad <69173633+ivarflakstad@users.noreply.github.com >
2023-11-20 14:12:57 +01:00
df6814f34e
Refactor to simplify our lives for settings the params in the encoder.
2023-11-20 14:12:57 +01:00
39406a6721
Adding the actual backend
2023-11-20 14:12:56 +01:00
976ad9f9c2
Remove tracing.
2023-11-20 14:12:29 +01:00
a4c4a56429
Metal part 1 - Scaffolding for metal.
2023-11-20 14:12:05 +01:00
f49bf6a81d
Fix OpenChat 3.5 tokenizer ( #1347 )
2023-11-19 18:48:04 +00:00
992a788da1
Add OpenChat 3.5 to quantized examples ( #1346 )
...
* Add OpenChat to quantized examples
* Add chat prompt
* Make the openchat example more in line with the other models.
* Fix a typo.
---------
Co-authored-by: laurent <laurent.mazare@gmail.com >
2023-11-19 18:28:52 +00:00
8d8f48c60c
feat: add test for individual onnx ops ( #1332 )
...
* feat: add test for individual onnx ops
* fix: prefer consts when possible
* feat: add move op tests
2023-11-19 08:17:09 +01:00
