issues
search
huggingface
/
candle
Minimalist ML framework for Rust
Apache License 2.0
13.79k
stars
751
forks
source link
issues
Oldest
Newest
Most commented
Recently updated
Oldest
Least commented
Least recently updated
Example with model via `include_bytes!`?
#2186
boustrophedon
opened
8 hours ago
0
Implement `torch.bucketize`
#2185
EricLBuehler
opened
8 hours ago
0
Metal error "no metal implementation for rms-norm" for Llama3 variant
#2184
n8mellis
closed
11 hours ago
2
add top_k option to `LogitsProcessor` new method
#2183
jorgeantonio21
closed
1 day ago
2
Whisper microphone example outputs gibberish
#2182
krzysztofwos
opened
2 days ago
0
`sort_last_dim` fails on cuda
#2181
lucasavila00
opened
2 days ago
0
Fix VarBuilder::from_slice_safetensors
#2180
boustrophedon
closed
3 days ago
1
Add SliceSafetensors.
#2179
LaurentMazare
closed
3 days ago
0
Make it possible to use TF32 accumulation in F32 matmuls.
#2178
LaurentMazare
closed
3 days ago
0
VarBuilder::from_bytes?
#2177
boustrophedon
closed
3 days ago
6
Switch cudarc back to dynamic linking.
#2176
LaurentMazare
closed
5 days ago
0
Latest commit on cudarc seems to have broken running the examples codes
#2175
hololite
opened
6 days ago
10
Update cudarc requirement from 0.11.0 to 0.11.1
#2174
sidharthrajaram
closed
6 days ago
3
Upgrade cudarc dependency to v0.11.1
#2173
sidharthrajaram
closed
6 days ago
0
qwen sse api
#2172
sunnyregion
opened
1 week ago
1
How to run LLama-3 or Phi with more then 4096 prompt tokens?
#2171
baleksey
opened
1 week ago
0
Why is the answer of my Gemma example not as expected? Did I miss something?
#2170
coolbeevip
closed
1 week ago
4
Unsupported cuda toolkit version: `12040`
#2169
kdletters
opened
1 week ago
1
No backward pass for `RmsNorm` if tensor is contiguous
#2168
agerasev
opened
1 week ago
0
How to do a Axum's sse function for Candle?
#2167
sunnyregion
closed
1 week ago
2
Update metal requirement from 0.27.0 to 0.28.0
#2166
dependabot[bot]
opened
1 week ago
0
Update cudarc requirement from 0.10.0 to 0.11.0
#2165
dependabot[bot]
closed
1 week ago
0
Incorrect EOS token(s) in meta-llama/Meta-Llama-3-8B-Instruct example
#2164
socathie
opened
1 week ago
4
Error: Metal error Error while loading function: "Function 'cast_bf16_f16' does not exist" with llama3
#2163
yIllusionSky
opened
1 week ago
2
Use write rather than try-write on the metal rw-locks.
#2162
LaurentMazare
closed
1 week ago
0
Model to architecture mapping
#2161
BDUG
closed
1 week ago
2
Force the revision for the phi3-llama quantized models.
#2159
LaurentMazare
closed
1 week ago
0
Separate quantized phi-3 implementation.
#2157
LaurentMazare
closed
1 week ago
0
Pin the version used for the quantized phi 3 gguf file.
#2156
LaurentMazare
closed
1 week ago
0
Bump the version number to 0.5.1.
#2155
LaurentMazare
closed
1 week ago
0
Quantized Phi-3 example fails "cannot find llama.attention.head_count in metadata"
#2154
MoonKraken
opened
1 week ago
4
`broadcast_as` error when processing multiple tokens at once in quantized example
#2153
EricLBuehler
opened
1 week ago
9
Problem loading metadata of gguf file
#2152
cnlancehu
opened
1 week ago
3
Support top-k in tthe llama example.
#2150
LaurentMazare
closed
1 week ago
0
Transparent Huge Pages Support
#2149
michaeleisel
opened
1 week ago
2
Tensor Filtering
#2148
michaeleisel
opened
1 week ago
0
Top-p halves the generation speed in the Llama example
#2147
Ayuei
closed
1 week ago
3
Musicgen forward implementation
#2145
qooba
opened
2 weeks ago
0
Low time effiency when run cnn on mnist-traning only with CPU
#2144
Viewer-HX
opened
2 weeks ago
3
F16/BF16 bugfix (bis).
#2143
LaurentMazare
closed
2 weeks ago
0
Bugfix the recent f16/bf16 changes.
#2142
LaurentMazare
closed
2 weeks ago
0
Add a toggle for F16/BF16 accumulation in gemm.
#2141
LaurentMazare
closed
2 weeks ago
0
"Illegal Instruction" on Older CPUS
#2140
jett06
opened
2 weeks ago
2
Candle won't use half-gemm from cublas when doing fp16 matmul
#2139
lucasavila00
closed
2 weeks ago
8
Add a forward_via_f16 method to the qmatmul op.
#2138
LaurentMazare
closed
2 weeks ago
0
Add the cuda dequantize f16 kernels.
#2137
LaurentMazare
closed
2 weeks ago
0
Adding direct-F16 quantization
#2136
EricLBuehler
closed
2 weeks ago
9
Apply the cast before the scaling.
#2135
LaurentMazare
closed
2 weeks ago
1
Add a sort function, similar to the PyToch one.
#2134
LaurentMazare
closed
2 weeks ago
0
Make the dtype configurable for phi.
#2133
LaurentMazare
closed
2 weeks ago
0
Next