index
:
forks/candle.git
main
summary
refs
log
tree
commit
diff
log msg
author
committer
range
path:
root
/
candle-core
Commit message (
Expand
)
Author
Age
Files
Lines
*
Fix the block size for some cuda kernels. (#1767)
Laurent Mazare
2024-02-27
2
-45
/
+15
*
Cuda kernel for dequantizing q8k. (#1760)
Laurent Mazare
2024-02-26
2
-22
/
+20
*
Cuda acceleration for quantized model. (#1754)
Laurent Mazare
2024-02-25
8
-69
/
+458
*
Support for attention bias in gemma + refactor things a bit. (#1744)
Laurent Mazare
2024-02-22
1
-46
/
+28
*
Add grads for interpolate1d (#1742)
Kirpal Grewal
2024-02-22
4
-6
/
+51
*
Add a couple backtraces on cpu errors. (#1738)
Laurent Mazare
2024-02-20
1
-3
/
+3
*
Bugfix for conv-transpose1d (#1734)
Laurent Mazare
2024-02-19
2
-0
/
+15
*
Support for groups in conv-transpose1d. (#1731)
Laurent Mazare
2024-02-18
3
-19
/
+43
*
Fix float unpickling. (#1730)
Laurent Mazare
2024-02-18
1
-2
/
+5
*
Module implementation for options. (#1728)
Laurent Mazare
2024-02-18
1
-0
/
+9
*
feat: add silu activation function (#1706)
OlivierDehaene
2024-02-14
8
-0
/
+169
*
Qmetal tweaks (#1704)
Laurent Mazare
2024-02-13
3
-100
/
+141
*
Fixing quantized llama demo on metal. (#1703)
Nicolas Patry
2024-02-13
3
-0
/
+19
*
Detach the tensors on batch-norm eval. (#1702)
Laurent Mazare
2024-02-13
3
-4
/
+8
*
ConvTranspose1d cuda support. (#1697)
Laurent Mazare
2024-02-12
2
-16
/
+66
*
Support defaultdict in PyTorch checkpoints. (#1696)
Laurent Mazare
2024-02-12
1
-2
/
+4
*
Pickle support: dig within the _rebuild_parameter calls. (#1681)
Laurent Mazare
2024-02-08
1
-0
/
+7
*
Add support for loading Fortran contiguous tensors (#1672)
Dilshod Tadjibaev
2024-02-07
4
-3
/
+61
*
Enhance pickle to retrieve state_dict with a given key (#1671)
Dilshod Tadjibaev
2024-02-06
5
-8
/
+60
*
Fix rustfmt. (#1669)
Laurent Mazare
2024-02-06
1
-1
/
+1
*
Fix clippy lints. (#1667)
Laurent Mazare
2024-02-06
1
-4
/
+5
*
Fix: pth files don't load on Windows (#1661)
Roma Klapaukh
2024-02-06
4
-3
/
+15
*
add roll function to tensor (#1666)
Jiayu Liu
2024-02-06
1
-0
/
+28
*
Merge branch 'main' into ivarflakstad/metal-prng
Ivar Flakstad
2024-01-17
8
-352
/
+1024
|
\
|
*
Quantized GGUF style (#1523)
Nicolas Patry
2024-01-17
7
-351
/
+1023
|
*
Expose the ndarray trait. (#1586)
Laurent Mazare
2024-01-14
1
-1
/
+1
*
|
Update metal random kernel and set_seed method
Ivar Flakstad
2024-01-17
1
-20
/
+13
*
|
Seed should be updated by random kernel result.
Ivar Flakstad
2024-01-15
1
-7
/
+28
*
|
Merge branch 'main' into ivarflakstad/metal-prng
Ivar Flakstad
2024-01-14
7
-4
/
+143
|
\
|
|
*
Add the pow operator. (#1583)
Laurent Mazare
2024-01-13
2
-3
/
+25
|
*
Fix format. (#1576)
Nicolas Patry
2024-01-12
1
-1
/
+5
|
*
Metal: Activate bfloat affine and add benchmark (#1543)
ivarflakstad
2024-01-12
4
-1
/
+47
|
*
Metal: f16 and bf16 where_cond + benchmark (#1545)
ivarflakstad
2024-01-12
4
-1
/
+67
*
|
Merge branch 'main' into ivarflakstad/metal-prng
Ivar Flakstad
2024-01-12
10
-219
/
+252
|
\
|
|
*
Bugfix for dequantizing q5k layers. (#1569)
Laurent Mazare
2024-01-11
2
-5
/
+5
|
*
feat(bf16): add cast support + tests for cast + bin ops (#1524)
Kyle McCarthy
2024-01-11
2
-3
/
+52
|
*
Seperate benchmarks by enabled features (#1538)
ivarflakstad
2024-01-11
4
-13
/
+82
|
*
Add a dequantize command to tensor-tools. (#1565)
Laurent Mazare
2024-01-11
1
-1
/
+24
|
*
Add relu kernel for metal (#1488)
Juarez Bochi
2024-01-10
1
-0
/
+4
|
*
Handle start-offset when loading a tensor from a pickle file. (#1546)
Laurent Mazare
2024-01-08
1
-3
/
+11
|
*
Simpler repro for the neon optimization issue + bugfix (#1544)
Laurent Mazare
2024-01-07
2
-168
/
+97
|
*
Simplifying our internal cargo dependencies. (#1529)
Nicolas Patry
2024-01-07
1
-2
/
+2
*
|
Updated feature separated benchmarks
Ivar Flakstad
2024-01-09
4
-26
/
+14
*
|
Merge branch 'ivarflakstad/seperate-benchmarks-by-feature' into ivarflakstad/...
Ivar Flakstad
2024-01-09
4
-11
/
+66
|
\
\
|
*
|
Improve benchmarks layout
Ivar Flakstad
2024-01-09
4
-6
/
+9
|
*
|
Avoid some unnecessary returns.
Laurent
2024-01-08
1
-4
/
+4
|
*
|
Remove allow pragma
Ivar Flakstad
2024-01-08
2
-6
/
+2
|
*
|
Use cfg to seperate benchmark results based on features
Ivar Flakstad
2024-01-07
2
-8
/
+64
|
|
/
*
|
Merge branch 'main' into ivarflakstad/metal-prng
Ivar Flakstad
2024-01-07
1
-34
/
+144
|
\
|
|
*
Adding bfloat16 support for the cast kernels. (#1520)
Nicolas Patry
2024-01-04
1
-0
/
+4
[next]