Gonzales

Fernanda24's activity

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

New activity in cerebras/DeepSeek-V3.2-REAP-508B-A37B 2 months ago

FP8 versions of DeepSeek-V3.2 would awesome!

2

#1 opened 2 months ago by

Fernanda24

New activity in cerebras/DeepSeek-V3.2-REAP-345B-A37B 2 months ago

ValueError: gemm_fp8_nt_groupwise is only supported on SM100, SM103 in trtllm backend.

#3 opened 2 months ago by

Fernanda24

New activity in eousphoros/DeepSeek-V3.2-NVFP4 2 months ago

Is it possible to make smaller NVFP4 quant at 340-360GB to fit in 4x96gb?

👍 1

68

#1 opened 3 months ago by

Fernanda24

New activity in Kebob/DeepSeek-V3.2-CPU-NUMA2-AMXINT4 3 months ago

attention backend

1

#1 opened 3 months ago by

Fernanda24

New activity in QuantTrio/DeepSeek-V3.2-AWQ 3 months ago

Aww Man!

20

#1 opened 3 months ago by

mtcl

New activity in Intel/DeepSeek-V3.1-Terminus-int4-mixed-AutoRound 3 months ago

Question will it work in vllm or sglang with rtx 6000 blackwells? cuda arch sm120

6

#1 opened 5 months ago by

Fernanda24

New activity in QuantTrio/DeepSeek-V3.1-AWQ-Lite 3 months ago

ooof this fits in 4x96gb can we get this for the new 3.2 Speciale ase well please :)

16

#2 opened 3 months ago by

Fernanda24

New activity in tencent/DeepSeek-V3.1-Terminus-W4AFP8 3 months ago

4 x RTX PRO 6000

👍 1

2

#1 opened 3 months ago by

willfalco

New activity in eousphoros/DeepSeek-V3.2-NVFP4 3 months ago

How did you bypass deepseek-v32 not recognized in Tranformers?

3

#3 opened 3 months ago by

Fernanda24

New activity in deepseek-ai/DeepSeek-V3.2 3 months ago

model type `deepseek_v32` not found

5

#16 opened 3 months ago by

harryhan618

New activity in mistralai/Ministral-3-14B-Instruct-2512 3 months ago

Update README.md

1

#4 opened 3 months ago by

Fernanda24

broken link to mistral small

1

#3 opened 3 months ago by

Fernanda24

New activity in QuantTrio/DeepSeek-V3.2-AWQ 3 months ago

Aww Man!

20

#1 opened 3 months ago by

mtcl

New activity in eousphoros/DeepSeek-V3.2-NVFP4 3 months ago

Is it possible to make smaller NVFP4 quant at 340-360GB to fit in 4x96gb?

👍 1

68

#1 opened 3 months ago by

Fernanda24

New activity in apple/starflow 3 months ago

Cool!

#6 opened 3 months ago by

Fernanda24

New activity in unsloth/DeepSeek-V3.2-Speciale 3 months ago

Thanks!

#1 opened 3 months ago by

Fernanda24

New activity in QuantTrio/DeepSeek-V3.1-AWQ-Lite 3 months ago

ooof this fits in 4x96gb can we get this for the new 3.2 Speciale ase well please :)

16

#2 opened 3 months ago by

Fernanda24

New activity in Intel/DeepSeek-V3.1-Terminus-int4-mixed-AutoRound 3 months ago

can we get this for the new Deepseek v3.2?

👍 1

#2 opened 3 months ago by

Fernanda24

Question will it work in vllm or sglang with rtx 6000 blackwells? cuda arch sm120

6

#1 opened 5 months ago by

Fernanda24

New activity in lukealonso/MiniMax-M2-NVFP4 3 months ago

you know which nightly it worked with? because it does not with current one

31

#1 opened 4 months ago by

willfalco