How to reproduce the accuracy result?
#15 opened 3 months ago
by
Yi30
quantize deepseek-r1-0528 please
👍
2
3
#14 opened 5 months ago
by
aabbccddwasd
make model generate think tag
#13 opened 6 months ago
by
michaelfeil
Update config.json
#12 opened 6 months ago
by
michaelfeil
can this model run on A800 ?
2
#10 opened 8 months ago
by
wang35
FP4 in attention proj
2
#9 opened 8 months ago
by
yoursmin
can this model run on Hopper GPU
6
#8 opened 8 months ago
by
simonlindelta
Can this model work with vLLM?
3
#7 opened 8 months ago
by
KimChen
Request for Detailed Benchmarking Setup with TensorRT-LLM on B200
➕
4
1
#6 opened 8 months ago
by
StardusterLiu
Benchmark results compared to orig fp8 / int4 quants etc?
➕
15
6
#1 opened 8 months ago
by
CHNtentes