ghostplant

ghostplant's activity

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

New activity in deepseek-ai/DeepSeek-V3.2 2 months ago

DSA Question

1

#33 opened 2 months ago by

ghostplant

New activity in microsoft/VibeVoice-Realtime-0.5B 2 months ago

For those who need a simplified execution on NVIDIA GPU

🔥 1

#21 opened 2 months ago by

ghostplant

New activity in deepseek-ai/DeepSeek-V3.2-Exp 5 months ago

Question about long-context evaluation in DeepSeek-V3.2-Exp

1

#15 opened 5 months ago by

fcMpKYz6Avp5QK

New activity in openai/gpt-oss-120b 7 months ago

Can gpt-oss support local vllm deployment on a100 GPU?

10

#73 opened 7 months ago by

Cola-any

New activity in openai/gpt-oss-20b 7 months ago

Running gpt-oss Without FlashAttention 3 – Any Alternatives to Ollama?

3

#72 opened 7 months ago by

shinho0902

New activity in openai/gpt-oss-120b 7 months ago

Run GPT-OSS-120B with just Single A100 (80GB)

2

#80 opened 7 months ago by

ghostplant

New activity in Qwen/Qwen3-Coder-480B-A35B-Instruct 7 months ago

How is Qwen3's inv_freq computed from scratch?

#13 opened 7 months ago by

ghostplant

New activity in moonshotai/Kimi-K2-Instruct 7 months ago

Run 1T-param on A100/H100(80G)x8 using FP4

🚀 🔥 5

7

#9 opened 8 months ago by

ghostplant

New activity in nvidia/DeepSeek-R1-NVFP4 8 months ago

quantize deepseek-r1-0528 please

👍 2

3

#14 opened 9 months ago by

aabbccddwasd

New activity in deepseek-ai/DeepSeek-R1-0528 9 months ago

刚部署满血deepseek r1 0528版本，推理性能提升这么多嘛？不是架构没变嘛？

12

#75 opened 9 months ago by

jakyer

How to run 0528version on GPU which don't support FP8

4

#64 opened 9 months ago by

Micdiane

这个问题大家的输出是什么？

6

#49 opened 9 months ago by

ghostplant

New activity in unsloth/DeepSeek-R1-GGUF 10 months ago

Share a mmlu test result,I use 2.51bit,and compare with ds api, baidu's ds,it seems 2.51bit is very smart at least in mmlu

2

#42 opened 12 months ago by

tarjintor

New activity in deepseek-ai/DeepSeek-R1 11 months ago

Does R1 support long context (> 4K)?

#172 opened about 1 year ago by

ghostplant

New activity in nvidia/DeepSeek-R1-NVFP4 11 months ago

can this model run on Hopper GPU

6

#8 opened 12 months ago by

simonlindelta

can this model run on A800 ?

2

#10 opened 11 months ago by

wang35

Why not use FP2 or IQ2 as kTransformers does?

#11 opened 11 months ago by

ghostplant

New activity in deepseek-ai/DeepSeek-R1 about 1 year ago

Deploying production ready service with Unsloth GGUF quants on your AWS account. (4 x L40S)

🔥 2

8

#171 opened about 1 year ago by

samagra-tensorfuse

90+ tokens per second for MI300x8 using batch_size = 1

1

#166 opened about 1 year ago by

ghostplant

New activity in unsloth/DeepSeek-R1-GGUF about 1 year ago

Q2_K_XL 好还是 Q4好呢

3

#34 opened about 1 year ago by

jializou