Jiangtao Zh

jiangtaozh's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

New activity in google/gemma-4-31B-it 12 days ago

vllm docker version vllm/vllm-openai:gemma4 detect Qwen3ForCausalLM model architecture and only allow max_model_len 40960

2

#20 opened 12 days ago by

jiangtaozh

New activity in latent-consistency/lcm-lora-sdxl 6 months ago

about the lcm lora base model

1

#13 opened 6 months ago by

jiangtaozh

New activity in coqui/XTTS-v2 7 months ago

CUDA Assertion Errors with Concurrent Requests on XTTS-v2

1

#107 opened about 1 year ago by

Chan-Y

New activity in yuhuili/EAGLE-mixtral-instruct-8x7B 10 months ago

kv_cache_utils.py NotImplementedError

#3 opened 10 months ago by

jiangtaozh

New activity in yuhuili/EAGLE3-LLaMA3.3-Instruct-70B 10 months ago

KeyError: 'embed_tokens.weight'

1

#5 opened 10 months ago by

jiangtaozh

New activity in mistralai/Mistral-7B-Instruct-v0.2 almost 2 years ago

deepspeed inference tensor parallelism memory footprint doesn't decrease with deepspeed tp_size increase.

6

#92 opened almost 2 years ago by

jiangtaozh

deepspeed inference tensor parallelism memory footprint doesn't decrease with deepspeed tp_size increase.

6

#92 opened almost 2 years ago by

jiangtaozh

deepspeed inference tensor parallelism memory footprint doesn't decrease with deepspeed tp_size increase.

6

#92 opened almost 2 years ago by

jiangtaozh