jayakommuru
jayakommuru
@winstxnhdw @alvaroalfaro612 can you share the correct message prompt template?
FYI, we were using 24.07 with no caching, still got this error couple of times although it was rare ``` E0420 21:02:21.661436313 345 sync.cc:1005] ASSERTION FAILED: prior > 0 Signal...
@appearancefnp @pskiran1 @MatthieuToulemont can you please confirm if this issue can be resolved by upgrading to 24.11 ? Facing same issue in 24.07
@yutkin @indrajit96 Were you able to solve this. we are also facing same issue. let us know if there's a fix. TIA !
+1 @QiJune @byshiue Cant we convert huggingface gemma 2 7b model to tensor RT LLM checkpoint ?
@QiJune @byshiue @AdamzNV Can you please confirm if gemma 2 is supported currently? if not, by when would the support for it would be available? Thanks
@AdamzNV cant we use gemma's convert_checkpoint code to convert gemma-2 to tensorRT_LLM format? as Llama's convert_checkpoint is working fine for llama-2 as well.