Hugging Face's logo
LagPixelLOL's picture
72

LagPixelLOL

v2ray
StationaryWeaver's profile picture rincel's profile picture joshnader's profile picture
·

AI & ML interests

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

Recent Activity

new activity about 16 hours ago
cognitivecomputations/DeepSeek-V3-AWQ:The V3-AWQ model's response seems not as expected
updated a model 2 days ago
v2ray/nai-lora-iewa
published a model 2 days ago
v2ray/nai-lora-iewa
View all activity

Organizations

v2AI Foundation's profile picture Unofficial Mistral Community's profile picture Social Post Explorers's profile picture Cognitive Computations's profile picture Hugging Face Discord Community's profile picture

v2ray's activity

New activity in cognitivecomputations/DeepSeek-V3-AWQ about 16 hours ago

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

4
#8 opened 1 day ago by
juxing
updated a model 2 days ago
published a model 2 days ago
New activity in cognitivecomputations/DeepSeek-R1-AWQ 3 days ago

Can't get 48 TPS on 8x H800

1
#21 opened 3 days ago by
Light4Bear
New activity in v2ray/GPT4chan-8B 3 days ago

gpt-4chan Neo-J

1
#1 opened 3 days ago by
gman402
New activity in cognitivecomputations/DeepSeek-R1-AWQ 3 days ago

Pipeline Parallellism

1
#20 opened 3 days ago by
leo98xh

8*a100 OUT OF MEMORY

1
#19 opened 3 days ago by
Jaren

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

1
#18 opened 4 days ago by
uv0xab
New activity in cognitivecomputations/DeepSeek-R1-AWQ 4 days ago

Significant Speed Drop with Increasing Input Length on H800 GPUs

2
#17 opened 4 days ago by
wangkkk956
updated a model 4 days ago
New activity in cognitivecomputations/DeepSeek-V3-AWQ 4 days ago

Docker start with vllm failed. Official vllm docker image 0.7.3

1
#7 opened 4 days ago by
kuliev-vitaly
New activity in cognitivecomputations/DeepSeek-R1-AWQ 4 days ago

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

13
#10 opened 12 days ago by
bupalinyu

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

3
#14 opened 5 days ago by
FightLLM

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

2
#16 opened 5 days ago by
xueshuai
New activity in cognitivecomputations/DeepSeek-R1-AWQ 5 days ago

skips the thinking process

11
#5 opened 17 days ago by
muzizon

Any one can run this model with SGlang framework？

2
#13 opened 5 days ago by
muziyongshixin
updated a model 8 days ago
published a model 8 days ago
New activity in v2ray/deepgelbooru 8 days ago

Any thresholds recommendation for this model?

3
#1 opened 10 days ago by
narugo
New activity in cognitivecomputations/DeepSeek-V3-AWQ 8 days ago

GPTQ Support

2
#1 opened about 2 months ago by
warlock-edward