LagPixelLOL's picture

77

LagPixelLOL

v2ray

·

LagPixelLOL

AI & ML interests

Looking for compute sponsors, please contact me through my email [email protected]!

Recent Activity

updated a model about 20 hours ago

x2ray/wheels

updated a dataset 4 days ago

v2ray/r-chatgpt-general-dump

new activity 4 days ago

cognitivecomputations/DeepSeek-R1-AWQ:About the group size

View all activity

Organizations

v2ray's activity

New activity in cognitivecomputations/DeepSeek-R1-AWQ 4 days ago

About the group size

#26 opened 4 days ago by

New activity in cognitivecomputations/DeepSeek-R1-AWQ 10 days ago

The awq quantization model may encounter garbled characters when performing inference on long texts.

#24 opened 12 days ago by

New activity in cognitivecomputations/DeepSeek-R1-AWQ 11 days ago

How can I quantify my BF16 format model into AWQ?

#25 opened 11 days ago by

New activity in cognitivecomputations/DeepSeek-R1-AWQ 13 days ago

Support for inference with MTP module?

#23 opened 13 days ago by

New activity in cognitivecomputations/DeepSeek-V3-AWQ 16 days ago

poor performance for DeepSeek-V3-AWQ

#9 opened 18 days ago by

New activity in cognitivecomputations/DeepSeek-V3-AWQ 17 days ago

The V3-AWQ model's response seems not as expected

#8 opened 20 days ago by

New activity in cognitivecomputations/DeepSeek-R1-AWQ 22 days ago

Can't get 48 TPS on 8x H800

#21 opened 22 days ago by

New activity in v2ray/GPT4chan-8B 22 days ago

gpt-4chan Neo-J

#1 opened 22 days ago by

New activity in cognitivecomputations/DeepSeek-R1-AWQ 22 days ago

Pipeline Parallellism

#20 opened 22 days ago by

8*a100 OUT OF MEMORY

#19 opened 22 days ago by

requests get stuck when sending long prompts (already solved, but still don't know why?)

#18 opened 22 days ago by

New activity in cognitivecomputations/DeepSeek-R1-AWQ 23 days ago

Significant Speed Drop with Increasing Input Length on H800 GPUs

#17 opened 23 days ago by

New activity in cognitivecomputations/DeepSeek-V3-AWQ 23 days ago

Docker start with vllm failed. Official vllm docker image 0.7.3

#7 opened 23 days ago by

New activity in cognitivecomputations/DeepSeek-R1-AWQ 23 days ago

when i use vllm v0.7.2 to deploy r1 awq, i got empty content

#10 opened about 1 month ago by

why "MLA is not supported with awq_marlin quantization. Disabling MLA." with 4090 * 32 (4 node / vllm 0.7.2)

#14 opened 24 days ago by

when i run command ,it didnot work. ( via vllm 0.7.3)

#16 opened 23 days ago by

New activity in cognitivecomputations/DeepSeek-R1-AWQ 24 days ago

skips the thinking process

#5 opened about 1 month ago by

Any one can run this model with SGlang framework？

#13 opened 24 days ago by

New activity in v2ray/deepgelbooru 27 days ago

Any thresholds recommendation for this model?

#1 opened 29 days ago by

New activity in cognitivecomputations/DeepSeek-V3-AWQ 27 days ago

GPTQ Support

#1 opened 2 months ago by