issues
search
huggingface
/
optimum-nvidia
Apache License 2.0
867
stars
86
forks
source link
issues
Newest
Newest
Most commented
Recently updated
Oldest
Least commented
Least recently updated
How to use TensorRT model converter
#149
FortunaZhang
opened
1 day ago
0
Add no code export infrastructure through CLI
#148
mfuntowicz
opened
4 days ago
0
Bring back quantization with Nvidia ModelOpt
#147
mfuntowicz
opened
4 days ago
0
OutOfMemory - Not able to run the text-generation.py example on V100, and A10G cores.
#146
yahavb
opened
3 weeks ago
0
feat(tests) : Update CI to use new workflow and silicon.
#145
mfuntowicz
closed
1 month ago
0
Unable to install `optimum-nvidia` on Ubuntu
#144
QuantumStaticFR
opened
2 months ago
2
Error on Quickstart example
#143
laikhtewari
opened
2 months ago
1
Error for gated model access despite valid HF_TOKEN
#142
laikhtewari
opened
2 months ago
0
Expected all tensors to be on the same device, but found at least two devices, cpu and cuda:0!
#141
d142796
opened
2 months ago
1
Model of type falcon is not supported
#140
puneeshkhanna
opened
2 months ago
0
Fix namespace error of dtype args
#139
puneeshkhanna
opened
2 months ago
0
CI new l4 runners
#138
mfuntowicz
closed
2 months ago
0
Enable automatic build of container at each release
#137
mfuntowicz
closed
2 months ago
0
Enable trufflehog scanner CI on GA
#136
mfuntowicz
closed
2 months ago
0
Upgrade to 0.10.0
#135
mfuntowicz
closed
2 months ago
0
Model of type gpt_bigcode is not supported
#134
Aryabhattacharjee
opened
2 months ago
0
Refactor the overall Hugging Face -> TRTLLM export workflow
#133
mfuntowicz
closed
2 months ago
0
feat(package): make sure we dont have init as optimum level
#132
mfuntowicz
closed
3 months ago
0
Mixtral
#131
mfuntowicz
closed
3 months ago
0
Providing input_embeddings for generation instead of IDs
#129
verityw
opened
3 months ago
0
No engine file found for LLama 3 and Cuda API error with LLama 2 with use_fp8
#128
PhilSapiens
opened
3 months ago
1
Can't Run README Code
#127
hammoudhasan
opened
3 months ago
0
Load from local path?
#126
bdambrosio
opened
4 months ago
0
Use a percentage based matching rather than exact token match for tests
#125
mfuntowicz
closed
4 months ago
0
Update to TensorRT-LLM v0.9.0
#124
mfuntowicz
closed
4 months ago
0
Is there support for StoppingCriteria?
#123
RomanKoshkin
opened
4 months ago
0
Docker container fails on RTX A6000
#122
RomanKoshkin
opened
4 months ago
0
Failed to import optimum.nvidia
#121
abpani
opened
4 months ago
0
Add support for Phi family of models
#120
mfuntowicz
opened
4 months ago
0
ValueError: mutable default <class 'tensorrt_llm.lora_manager.LoraBuildConfig'> for field lora_config is not allowed: use default_factory
#119
manish-marwah
opened
4 months ago
5
Remove claim of Turing support
#118
laikhtewari
closed
4 months ago
0
Test batched causallm inference
#117
fxmarty
closed
4 months ago
1
FileNotFoundError: [Errno 2] No such file or directory: 'trtllm-build'
#116
Quang-elec44
opened
4 months ago
0
Fix checking output limits for #114
#115
zaycev
closed
4 months ago
1
Batching seems to be broken.
#114
zaycev
closed
4 months ago
1
Mention important additional parameters for engine config in README
#113
zaycev
closed
4 months ago
2
Bump version to 0.1.0b6
#112
mfuntowicz
closed
4 months ago
0
Avoid reloading available transformers config
#111
fxmarty
closed
4 months ago
0
Test CausalLM generate & pipeline
#110
fxmarty
closed
4 months ago
1
Use pinned version for huggingface-hub
#109
mfuntowicz
closed
5 months ago
0
Fix quality on the main branch
#108
mfuntowicz
closed
5 months ago
0
Whisper inference
#107
fxmarty
closed
5 months ago
0
When can I support llava
#106
xusk
opened
5 months ago
0
Pip installation instruction is broken
#105
zaycev
closed
4 months ago
4
Fix invalid dependencies
#104
mfuntowicz
closed
5 months ago
0
RuntimeError: Failed to import transformers.modeling_utils
#103
Quang-elec44
closed
4 months ago
0
Instructions on how to set TP/PP
#102
fxmarty
opened
5 months ago
0
Add back the ability to build Whisper from Transformers checkpoints
#101
fxmarty
closed
5 months ago
1
Avoid writting engines in `.cache/huggingface/hub`
#100
fxmarty
opened
5 months ago
0
Add `optimum-cli export tensorrt-llm`
#99
fxmarty
opened
5 months ago
0
Next