issues
search
replicate
/
cog-llama-template
LLaMA Cog template
Apache License 2.0
307
stars
52
forks
source link
issues
Newest
Newest
Most commented
Recently updated
Oldest
Least commented
Least recently updated
replicate.stream(...) is not a function or its return value is not async iterable
#88
hsmandavi111
opened
8 months ago
0
pydantic depdency conflics between fastapi and mlc-ai
#87
sinopec
opened
10 months ago
2
TVMError: The output probabilities are all NaNs, can not sample from it
#86
zeke
opened
10 months ago
1
RuntimeError: top_k is currently not supported by our generation engine.
#85
zeke
opened
10 months ago
0
Does meta/llama-2-70b-chat use the original model weights?
#84
fancyerii
opened
11 months ago
0
Joe/mixtral vllm
#83
joehoover
opened
11 months ago
1
:sparkles: add optional wandb logging
#82
nateraw
opened
11 months ago
2
reduce max-conn-per-host
#81
philandstuff
closed
10 months ago
0
use prompt template for base models
#80
technillogue
closed
12 months ago
0
convert_to_tensors.py doesn't exist
#79
aryn832
opened
1 year ago
2
add prompt_template parameter
#78
technillogue
closed
1 year ago
0
fix check_files_exist for nested paths
#77
technillogue
opened
1 year ago
0
Base PR with many things merged
#76
moinnadeem
opened
1 year ago
0
properly decode emoji
#75
daanelson
closed
1 year ago
0
cuda tho
#74
daanelson
closed
1 year ago
0
new pget i guess?
#73
technillogue
closed
1 year ago
2
[XS] Update Docker Ignore
#72
moinnadeem
closed
1 year ago
2
[XS] Removing model artifacts
#71
moinnadeem
closed
1 year ago
0
[XS] Change code enabling MLC to run tensor parallelism
#70
moinnadeem
closed
1 year ago
0
[XS] Add FP16 Non-Chat Models
#69
moinnadeem
closed
1 year ago
0
Fix 7b
#68
daanelson
opened
1 year ago
0
Dan/cleanup
#67
daanelson
closed
1 year ago
1
delay prints with a decorator
#66
technillogue
closed
1 year ago
3
[XS] Add Mistral models to MLC
#65
moinnadeem
closed
1 year ago
0
improve how downloader writes to disk
#64
technillogue
opened
1 year ago
0
cognix build system
#63
technillogue
opened
1 year ago
0
updated config
#62
daanelson
closed
1 year ago
0
use python downloader instead of pget
#61
technillogue
closed
1 year ago
2
use arg remover from main
#60
technillogue
closed
1 year ago
0
productionize mlc
#59
daanelson
closed
1 year ago
1
Revert "productionize mlc"
#58
daanelson
closed
1 year ago
0
ceiling on pget
#57
daanelson
closed
1 year ago
0
Dan/mlc fix two
#56
daanelson
closed
1 year ago
0
productionize mlc
#55
technillogue
closed
1 year ago
0
document the release process
#54
zeke
closed
1 year ago
1
Merge hybrid MLC + vLLM engine into MLC engines PR
#53
moinnadeem
closed
1 year ago
0
fix removing arguments
#52
technillogue
closed
1 year ago
0
Add Python tooling to project
#51
mattt
closed
1 year ago
1
working vllm engine
#50
daanelson
closed
1 year ago
0
feat: add MLC as a working engine
#49
moinnadeem
closed
1 year ago
3
Adding MLC as a working engine
#48
moinnadeem
closed
1 year ago
0
Engines
#47
daanelson
closed
1 year ago
0
Dan/vllm exllama engine
#46
daanelson
closed
1 year ago
0
WIP vllm exllama engine
#45
daanelson
closed
1 year ago
0
Dan/mistral lm
#44
daanelson
opened
1 year ago
0
Allow good benchmark prompting practices for chat models with simple prompt formatting tweak
#43
LRudL
opened
1 year ago
1
Add vLLM as an inference engine
#42
moinnadeem
closed
1 year ago
0
Adding weights urls configuration files
#41
jakedahn
closed
1 year ago
0
Add support for lora target modules
#40
joehoover
opened
1 year ago
1
clean config
#39
technillogue
closed
1 year ago
0
Next