Kyle Sayers

kylesayrs's activity

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

New activity in RedHatAI/Hy3-NVFP4-FP8 3 days ago

runs on two DGX Spark

❤️ 1

1

#1 opened 15 days ago by

cboergermann

New activity in RedHatAI/DeepSeek-V4-Flash-NVFP4-FP8 about 1 month ago

Fix kv_cache_scheme: DSV4 sparse attention requires FP8 KV cache

3

#4 opened about 1 month ago by

nathans-redhat-com

New activity in RedHatAI/GLM-5.2-NVFP4 about 1 month ago

Safetensors File Size < 50 GB?

2

#1 opened about 2 months ago by

FabianHeller

New activity in RedHatAI/GLM-5.2-NVFP4-FP8 about 1 month ago

Fix vLLM snippet in `README.md`

👍 1

1

#2 opened about 2 months ago by

alvarobartt

Add mtp regex to ignore list

2

#3 opened about 2 months ago by

bdellabe

New activity in Xenova/llama2.c-stories110M about 1 year ago

[Bug] Model loads with meta tensors

#4 opened about 1 year ago by

kylesayrs

New activity in ptb-text-only/ptb_text_only about 1 year ago

No longer supported by `datasets>=4.0.0`

👀 1

2

#3 opened about 1 year ago by

kylesayrs

New activity in unsloth/Qwen2.5-VL-72B-Instruct-unsloth-bnb-4bit over 1 year ago

Update preprocessor_config.json

2

#2 opened over 1 year ago by

TahirC

New activity in deepseek-ai/DeepSeek-V3 over 1 year ago

fix for transformers 4.49 compatibility.

2

#91 opened over 1 year ago by

katuni4ka

New activity in Xenova/llama2.c-stories15M over 1 year ago

Model fails to load with AutoModelForCausalLM

5

#4 opened over 1 year ago by

horheynm

New activity in moonshotai/Moonlight-16B-A3B over 1 year ago

Fix generation with latest transformers

#1 opened over 1 year ago by

kylesayrs

New activity in deepseek-ai/DeepSeek-V3 over 1 year ago

Fix generation with latest transformers

1

#87 opened over 1 year ago by

kylesayrs

Fix generation with latest transformers

1

#88 opened over 1 year ago by

kylesayrs

New activity in microsoft/Phi-3-vision-128k-instruct over 1 year ago

[Bug] Model Breaking Dynamic Cache

#69 opened over 1 year ago by

kylesayrs

New activity in mistral-experimental/pixtral-12b over 1 year ago

Getting shape mismatch while loading saved Pixtral model

4

#24 opened over 1 year ago by

ss007

New activity in zai-org/glm-4v-9b over 1 year ago

Fix tokenizer reloading

#42 opened over 1 year ago by

kylesayrs

How to run the Int4 quantized model？

2

#10 opened about 2 years ago by

CharlesLincoln

fix image size unchangeable

1

#32 opened about 2 years ago by

JDEdisonChen

Tokenizer参数保存到本地之后再重新读入会所改变？

🔥 1

1

#35 opened almost 2 years ago by

Tonynan

New activity in nm-testing/pixtral-12b-w4a16-actorder-group over 1 year ago

What is an actorder group and what are the advantages of running this in vLLM?

4

#1 opened over 1 year ago by

nickandbro