Gonzales's picture

Gonzales

Fernanda24

·

AI & ML interests

None yet

Recent Activity

liked a model 3 days ago

ubergarm/GLM-4.7-GGUF

new activity 9 days ago

cerebras/DeepSeek-V3.2-REAP-345B-A37B:ValueError: gemm_fp8_nt_groupwise is only supported on SM100, SM103 in trtllm backend.

new activity 10 days ago

cerebras/DeepSeek-V3.2-REAP-508B-A37B:FP8 versions of DeepSeek-V3.2 would awesome!

View all activity

Organizations

None yet

New activity in cerebras/DeepSeek-V3.2-REAP-345B-A37B 9 days ago

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

#3 opened 9 days ago by

New activity in cerebras/DeepSeek-V3.2-REAP-508B-A37B 10 days ago

FP8 versions of DeepSeek-V3.2 would awesome!

#1 opened 10 days ago by

New activity in eousphoros/DeepSeek-V3.2-NVFP4 12 days ago

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

#1 opened 24 days ago by

New activity in Kebob/DeepSeek-V3.2-CPU-NUMA2-AMXINT4 19 days ago

attention backend

#1 opened 19 days ago by

New activity in QuantTrio/DeepSeek-V3.2-AWQ 20 days ago

Aww Man!

#1 opened 24 days ago by

New activity in Intel/DeepSeek-V3.1-Terminus-int4-mixed-AutoRound 21 days ago

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

#1 opened 2 months ago by

New activity in QuantTrio/DeepSeek-V3.1-AWQ-Lite 21 days ago

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

#2 opened 25 days ago by

New activity in tencent/DeepSeek-V3.1-Terminus-W4AFP8 22 days ago

4 x RTX PRO 6000

#1 opened 25 days ago by

New activity in eousphoros/DeepSeek-V3.2-NVFP4 22 days ago

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

#3 opened 23 days ago by

New activity in deepseek-ai/DeepSeek-V3.2 23 days ago

model type `deepseek_v32` not found

#16 opened 25 days ago by

New activity in mistralai/Ministral-3-14B-Instruct-2512 24 days ago

Update README.md

#4 opened 24 days ago by

broken link to mistral small

#3 opened 24 days ago by

New activity in QuantTrio/DeepSeek-V3.2-AWQ 24 days ago

Aww Man!

#1 opened 24 days ago by

New activity in eousphoros/DeepSeek-V3.2-NVFP4 24 days ago

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

#1 opened 24 days ago by

New activity in apple/starflow 25 days ago

Cool!

#6 opened 25 days ago by

New activity in unsloth/DeepSeek-V3.2-Speciale 25 days ago

Thanks!

#1 opened 25 days ago by

New activity in QuantTrio/DeepSeek-V3.1-AWQ-Lite 25 days ago

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

#2 opened 25 days ago by

New activity in Intel/DeepSeek-V3.1-Terminus-int4-mixed-AutoRound 25 days ago

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

#2 opened 25 days ago by

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

#1 opened 2 months ago by

New activity in lukealonso/MiniMax-M2-NVFP4 25 days ago

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

#1 opened about 1 month ago by