huggingface/candle
1
0
Fork 0
mirror of https://github.com/huggingface/candle.git synced 2025-06-16 10:38:54 +00:00
Code Issues Packages Projects Releases Wiki Activity
1,729 Commits 74 Branches 16 Tags
beadb1b4345f6794a42cf28b3429f454235f96e8
Commit Graph

1729 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
Laurent Mazare
beadb1b434 Explicit candle version so that cargo publish can be used easily. (#1641) 2024-01-31 18:42:22 +01:00
Christopher Fleetwood
6d83d42efb Merge pull request #1606 from FL33TW00D/feature/larger-batches 
fix: larger batches
 2024-01-29 15:31:10 +00:00
FL33TW00D
b6afb46601 chore: final 2024-01-22 15:15:19 +00:00
ivarflakstad
fd7c856564 Merge pull request #1533 from huggingface/ivarflakstad/metal-prng 2024-01-22 07:30:20 +01:00
FL33TW00D
73d79e6092 chore: actual fix 2024-01-19 09:35:42 +00:00
FL33TW00D
b1879f17f6 chore: switch to buffer 2024-01-19 08:57:49 +00:00
FL33TW00D
4f79f5df8a fix: larger batches 2024-01-18 14:30:14 +00:00
ivarflakstad
1cf34368b7 Merge pull request #1602 from mimiquate/fix-metal-kernel-type 
Metal: Use uint8_t as output type in int64_t binary op kernel
 2024-01-18 08:40:34 +01:00
Gonzalo
17e6e2d7ee Fixes metal kernel u8 type 2024-01-17 15:47:08 -03:00
Ivar Flakstad
80b1c689f9 Revert public EncoderParam 2024-01-17 18:09:28 +01:00
Ivar Flakstad
db923517b3 Merge branch 'main' into ivarflakstad/metal-prng 2024-01-17 18:03:57 +01:00
Nicolas Patry
403680f17d Quantized GGUF style (#1523) 
* 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>
 2024-01-17 10:27:58 +01:00
Ivar Flakstad
86a8e58897 Update metal random kernel and set_seed method 
* set_seed via buffer content pointer copy + did_modify_range

* ensure random.metal kernel does not write outside of buffer range when tid==0
 2024-01-17 09:12:44 +01:00
Jani Monoses
5270224f40 Add MobileOne model. (#1595) 
* Add MobileOne model.

* Clippy fixes

* Remove a comment.

---------

Co-authored-by: laurent <laurent.mazare@gmail.com>
 2024-01-16 06:34:16 +01:00
dependabot[bot]
7e3349d7c3 Update parquet requirement from 45.0.0 to 50.0.0 (#1592) 
Updates the requirements on [parquet](https://github.com/apache/arrow-rs) to permit the latest version.
- [Changelog](https://github.com/apache/arrow-rs/blob/master/CHANGELOG-old.md)
- [Commits](https://github.com/apache/arrow-rs/compare/45.0.0...45.0.0)

---
updated-dependencies:
- dependency-name: parquet
  dependency-type: direct:production
...

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
 2024-01-15 22:35:01 +01:00
dependabot[bot]
1257fc6719 Update safetensors requirement from 0.3.1 to 0.4.1 (#1591) 
Updates the requirements on [safetensors](https://github.com/huggingface/safetensors) to permit the latest version.
- [Release notes](https://github.com/huggingface/safetensors/releases)
- [Changelog](https://github.com/huggingface/safetensors/blob/main/RELEASE.md)
- [Commits](https://github.com/huggingface/safetensors/compare/v0.3.1...v0.3.3)

---
updated-dependencies:
- dependency-name: safetensors
  dependency-type: direct:production
...

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
 2024-01-15 22:34:40 +01:00
Laurent Mazare
ea36f3b11f Use the new phi model by default. (#1589) 2024-01-15 12:30:27 +01:00
Ivar Flakstad
79478ff5a1 Seed should be updated by random kernel result. 2024-01-15 11:58:25 +01:00
Laurent Mazare
86b7c01b30 Update gemm to the latest version. (#1587) 2024-01-15 09:44:51 +01:00
Laurent Mazare
bdd8107fda Expose the ndarray trait. (#1586) 2024-01-14 20:09:49 +01:00
Ivar Flakstad
ecf88a6d38 Merge branch 'main' into ivarflakstad/metal-prng 2024-01-14 17:10:54 +01:00
Laurent Mazare
e6d86b0819 Add the pow operator. (#1583) 
* Add the pow operator.

* Support the pow operation in onnx.
 2024-01-13 20:24:06 +01:00
Laurent Mazare
88618255cb Fix the rotary embeddings for the new phi implementation. (#1582) 
* Fix the rotary embeddings for the new phi implementation.

* Match the activation.

* KV cache fix.

* Use the config activation function.
 2024-01-13 19:44:41 +01:00
Laurent Mazare
539ead927a Update the Phi model to use the updated architecture. (#1580) 
* Update the Phi model to use the updated architecture.

* Add more of the phi model.

* Repeat KV + caching.

* Apply the rotary embeddings.

* Add support for the new phi model in the phi example.

* Fix a couple glitches.

* Fix a couple more glitches.
 2024-01-13 17:38:27 +01:00
SebastianRueClausen
a46864bd56 Fix "Minimal Mamba" link in README. (#1577) 2024-01-12 17:47:07 +01:00
Nicolas Patry
bafe95b660 Fix format. (#1576) 2024-01-12 14:23:17 +01:00
ivarflakstad
a3d92ab226 Metal: Activate bfloat affine and add benchmark (#1543) 
* Use cfg to seperate benchmark results based on features

* Add bfloat affine and benchmarks

* Fix flops calculation

* Remove allow pragma

* Avoid some unnecessary returns.

* Improve benchmarks layout

---------

Co-authored-by: Laurent <laurent.mazare@gmail.com>
Co-authored-by: Nicolas Patry <patry.nicolas@protonmail.com>
 2024-01-12 11:19:49 +01:00
ivarflakstad
e90bcdcc7c Metal: f16 and bf16 where_cond + benchmark (#1545) 
* Use cfg to seperate benchmark results based on features

* Add metal where_cond for f16 and bf16. Add benchmark

* Remove allow pragma

* Avoid some unnecessary returns.

* Improve benchmarks layout

* Updated feature separated benchmarks

---------

Co-authored-by: Laurent <laurent.mazare@gmail.com>
 2024-01-12 11:18:11 +01:00
Laurent Mazare
8e06bfb4fd Mention VGG in the readme. (#1573) 2024-01-12 09:59:29 +01:00
Laurent Mazare
6242276c09 Pin the revision used for phi-v2 + make it the default. (#1572) 
* Pin the revision used for phi-v2 + make it the default.

* Tweak the custom-ops build.
 2024-01-12 09:19:30 +01:00
Ivar Flakstad
e06e8d0dbe fmt 2024-01-12 07:26:42 +01:00
Ivar Flakstad
e63bb8661b Merge branch 'main' into ivarflakstad/metal-prng 2024-01-12 07:19:58 +01:00
Laurent Mazare
41915184bb Bugfix for dequantizing q5k layers. (#1569) 2024-01-11 23:15:11 +01:00
ivarflakstad
c1876b8041 Merge pull request #1567 from bayedieng/close-ifdef 2024-01-11 22:14:38 +01:00
Baye Dieng
85e5680277 remove metal version check 2024-01-11 21:02:03 +00:00
Baye Dieng
1327419776 close ifdef 2024-01-11 17:14:12 +00:00
Kyle McCarthy
402349d120 feat(bf16): add cast support + tests for cast + bin ops (#1524) 2024-01-11 15:49:13 +01:00
ivarflakstad
9f0c99f0c1 Seperate benchmarks by enabled features (#1538) 
* Use cfg to seperate benchmark results based on features

* Remove allow pragma

* Avoid some unnecessary returns.

* Improve benchmarks layout

* Derive bench_name from actual device

* Run CPU benchmarks even when GPU feature is enabled

---------

Co-authored-by: Laurent <laurent.mazare@gmail.com>
 2024-01-11 15:35:38 +01:00
Laurent Mazare
0fc95c9f0c Add a dequantize command to tensor-tools. (#1565) 
* Add a dequantize command to tensor-tools.

* Clippy fixes.
 2024-01-11 11:21:01 +01:00
Jani Monoses
2480c5dbdd Add RepVGG model. (#1561) 
* Add RepVGG model.

* Add RepVGG README

* Extract var to top level

* Replace hashmap with a match

* Add a variant for the model kind + avoid some unnecessary config cloning.

---------

Co-authored-by: Laurent <laurent.mazare@gmail.com>
 2024-01-11 07:07:40 +01:00
Jani Monoses
63944714f2 Use candle_nn::embedding instead of local copies in a few models. (#1562) 2024-01-10 21:36:27 +01:00
ivarflakstad
d3bdd788cf Use __HAVE_BFLOAT__ to check for bfloat support instead of metal version check (#1540) 2024-01-10 18:50:30 +01:00
Juarez Bochi
ae06cb74bb Add relu kernel for metal (#1488) 
* Add relu kernel for metal

* Copy error messages proposed in #1491

* Revert non relu changes

* Fix name changes

* Fix the last of us (:

* Fix copy and paste mistakes

* Fix typo

* Revert order changes

* Revert order change

* Add deleted functions back

* Run rustfmt
 2024-01-10 18:27:17 +01:00
dependabot[bot]
a897fda74e Update memmap2 requirement from 0.7.1 to 0.9.3 (#1556) 
Updates the requirements on [memmap2](https://github.com/RazrFalcon/memmap2-rs) to permit the latest version.
- [Changelog](https://github.com/RazrFalcon/memmap2-rs/blob/master/CHANGELOG.md)
- [Commits](https://github.com/RazrFalcon/memmap2-rs/compare/v0.7.1...v0.7.1)

---
updated-dependencies:
- dependency-name: memmap2
  dependency-type: direct:production
...

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
 2024-01-10 16:27:59 +01:00
dependabot[bot]
1f1179913a Update gloo requirement from 0.8 to 0.11 (#1558) 
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>
 2024-01-10 16:27:20 +01:00
dependabot[bot]
6e98cf2a92 Update cudarc requirement from 0.9.14 to 0.10.0 (#1559) 
Updates the requirements on [cudarc](https://github.com/coreylowman/cudarc) to permit the latest version.
- [Release notes](https://github.com/coreylowman/cudarc/releases)
- [Commits](https://github.com/coreylowman/cudarc/compare/v0.9.14...v0.9.15)

---
updated-dependencies:
- dependency-name: cudarc
  dependency-type: direct:production
...

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
 2024-01-10 16:27:05 +01:00
dependabot[bot]
2cc1247999 Update tokenizers requirement from 0.13.4 to 0.15.0 (#1555) 
Updates the requirements on [tokenizers](https://github.com/huggingface/tokenizers) to permit the latest version.
- [Release notes](https://github.com/huggingface/tokenizers/releases)
- [Changelog](https://github.com/huggingface/tokenizers/blob/main/RELEASE.md)
- [Commits](https://github.com/huggingface/tokenizers/commits)

---
updated-dependencies:
- dependency-name: tokenizers
  dependency-type: direct:production
...

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
 2024-01-10 16:26:53 +01:00
darker
edf3fcd1c4 fix: deprecated option field (open-pull-requests-limit-per-dependency) (#1554) 2024-01-10 15:12:46 +01:00
darker
53e4755015 feat: add dependabot to the project (#1553) 
* feat: add dependabot to the project

* feat: add let's accept patches/fix from other libs

* Revert "feat: add let's accept patches/fix from other libs"

This reverts commit d31a956f81.
 2024-01-10 14:57:20 +01:00
Ivar Flakstad
87efb5d8eb Updated feature separated benchmarks 2024-01-09 19:04:31 +01:00