Is this cosmos?
#13 opened 6 days ago
by
Blazgo

sglang supports Llama-3_1-Nemotron-Ultra-253B-v1 ?
#12 opened 26 days ago
by
chuanyizjc

llama.cpp now supports Llama-3_1-Nemotron-Ultra-253B-v1
π
1
#11 opened 28 days ago
by
ymcki
Error invalid configuration argument at line 76 in file /user/...//bitsandbytes/csrc/ops.cu
#10 opened 29 days ago
by
bitmman-nch
Add link to Github repository and paper page
#9 opened about 1 month ago
by
nielsr

Model usage on vLLM fails: `No available memory for the cache blocks` & `Error executing method 'determine_num_available_blocks'`
2
#8 opened about 2 months ago
by
surajd

benchmark test use vllm ? input/output=500/2000 οΌ
2
#6 opened about 2 months ago
by
chuanyizjc

FP8 and FP4
2
#5 opened about 2 months ago
by
whatever1983
how to reproduce the benchmark score?
#4 opened about 2 months ago
by
lincharliesun
AWQ OR GPTQ Quant
π
1
1
#2 opened about 2 months ago
by
getfit

"ffn_mult": null,
β
1
9
#1 opened about 2 months ago
by
csabakecskemeti
