summaryrefslogtreecommitdiff
Commit message (Collapse)AuthorAgeFilesLines
* Bump the crate version to 0.3.3. (#1490)Laurent Mazare2023-12-2821-55/+55
|
* Add some mention to SOLAR-10.7B in the readme. (#1487)Laurent Mazare2023-12-271-2/+3
|
* Rework the llama example config, add the solar model. (#1485)Laurent Mazare2023-12-261-72/+36
|
* Use the new hub helper function. (#1484)Laurent Mazare2023-12-262-16/+2
|
* Helper function to load sharded safetensors files (#1481)Laurent Mazare2023-12-257-67/+40
| | | | | | | * Fix the quantized mistral example. * Add a helper function to load sharded safetensors weights. * Use the sharded loader.
* Merge pull request #1479 from huggingface/upsample_metalNicolas Patry2023-12-253-2/+137
|\ | | | | Adding upsample_nearest_2d.
| * Adding upsample_nearest_2d.Nicolas Patry2023-12-253-2/+137
|/
* Merge pull request #1461 from huggingface/metal-convNicolas Patry2023-12-255-86/+399
|\ | | | | Adding the convolutions (1d + 2d) to candle on metal.
| * Fixing matmul for convolutions.Nicolas Patry2023-12-252-3/+4
| |
| * Adding the convolutions (1d + 2d) to candle on metal.Nicolas Patry2023-12-215-84/+396
| |
* | Fix the quantized mistral example. (#1478)Laurent Mazare2023-12-252-4/+14
| |
* | Support mistral instruct v0.2. (#1475)Laurent Mazare2023-12-232-7/+18
| | | | | | | | | | * Support mistral instruct v0.2. * Use the safetensors model now that they are available.
* | MMLU evaluation for Phi. (#1474)Laurent Mazare2023-12-232-13/+105
| | | | | | | | | | * MMLU evaluation for Phi. * Improve the evaluation.
* | Validate the kernel size in pooling ops. (#1473)Laurent Mazare2023-12-231-12/+16
| | | | | | | | | | * Validate the kernel size in pooling ops. * Revert the changes to basics.
* | Fix for mamba 2.8b. (#1472)Laurent Mazare2023-12-231-1/+1
| |
* | Support different mamba models. (#1471)Laurent Mazare2023-12-232-7/+55
| |
* | Sketch the minimal mamba example. (#1465)Laurent Mazare2023-12-224-1/+458
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | * Sketch the minimal mamba example. * Fix rustfmt. * Forward pass for mamba. * Finish the forward pass. * Inference fixes. * Bugfixes. * More fixes. * Add a readme.
* | feat: add clear_kv_cache to mistral and qmistral models (#1464)drbh2023-12-212-0/+28
| |
* | make fn name generic (#1459)Daniel Clough2023-12-211-1/+2
| | | | | | Co-authored-by: Ubuntu <danielclough@users.noreply.github.com>
* | add fn config_chat_ml (#1458)Daniel Clough2023-12-201-0/+19
|/ | | | | | | | | | * add fn config_chat_ml * Add a link to the original config. --------- Co-authored-by: Ubuntu <danielclough@users.noreply.github.com> Co-authored-by: laurent <laurent.mazare@gmail.com>
* Merge pull request #1318 from huggingface/metal4Nicolas Patry2023-12-2025-776/+2775
|\ | | | | Starting to fix some tests.
| * Optimizing decode matmul (Phi at 28tok/s on M3).Nicolas Patry2023-12-204-5/+66
| | | | | | | | Adding some benchmark in order to help checking out matmul performance.
| * Clippy pass.Nicolas Patry2023-12-183-14/+11
| |
| * Remove print.Nicolas Patry2023-12-181-1/+0
| |
| * Missing cast.Nicolas Patry2023-12-182-0/+3
| |
| * Index add.Nicolas Patry2023-12-183-63/+151
| |
| * Scatter add.Nicolas Patry2023-12-183-17/+147
| |
| * Adding gather op.Nicolas Patry2023-12-173-17/+157
| |
| * Adding CMPNicolas Patry2023-12-173-85/+140
| |
| * Implement randn (CPU-> device)Nicolas Patry2023-12-171-4/+3
| |
| * Finish reduce kernels.Nicolas Patry2023-12-176-39/+258
| |
| * Addressing a lot of comments.Nicolas Patry2023-12-154-20/+33
| |
| * Remove `unwrap()`.Nicolas Patry2023-12-152-48/+77
| |
| * Remove test file.Nicolas Patry2023-12-151-209/+0
| |
| * Renamed all kernel names.Nicolas Patry2023-12-157-56/+56
| |
| * Better error message on older macosNicolas Patry2023-12-151-3/+5
| |
| * More cleanup.Nicolas Patry2023-12-152-6/+1
| |
| * Revert candle-transformers.Nicolas Patry2023-12-151-38/+4
| |
| * Adding a bunch of docs !Nicolas Patry2023-12-152-53/+122
| | | | | | | | Co-authored-by: Ivar Flakstad <69173633+ivarflakstad@users.noreply.github.com>
| * More cleanup.Nicolas Patry2023-12-151-15/+16
| |
| * cleanup.Nicolas Patry2023-12-151-27/+4
| |
| * Fixing softmax.Nicolas Patry2023-12-154-13/+14
| |
| * Fix softmax for long sequences (missing barrier).Nicolas Patry2023-12-143-18/+50
| |
| * Fix use resource.Nicolas Patry2023-12-141-0/+40
| |
| * Working with merging encoders and using fences.Nicolas Patry2023-12-145-94/+279
| |
| * Fixing tests + matmul from MFANicolas Patry2023-12-135-23/+128
| |
| * Removed MPSMatrix entirely (buggy).Nicolas Patry2023-12-133-194/+311
| |
| * Better version ?Nicolas Patry2023-12-132-25/+52
| |
| * Lots of updates including some stack of command buffers.nicolas2023-12-1210-117/+537
| |
| * Merge pull request #1408 from jbochi/metal_gelu2Nicolas Patry2023-12-092-5/+29
| |\ | | | | | | Fix NaN errors for Gelu in Metal
generated by cgit v1.2.3 (git 2.39.1) at 2025-04-13 04:40:19 +0000