Issues
- 3
Bug Report
#21 opened by Patrick-Ni - 8
- 4
- 3
请问 kv_cluster.update_kv 只在 prefill 时被调用吗?
#20 opened by DOG-wooooof - 6
A serious issue in your code
#15 opened by JulietLJY - 1
仅截取了输入数据的前4k和后4k token, 但longbench最长32k token?
#18 opened by JulietLJY - 1
Strange Results of Mistral
#13 opened by yuhuixu1993 - 4
Merge into vLLM, is it possible?
#14 opened by PatchouliTIS - 3
- 3
Settings and implementations of baselines
#16 opened by bingps - 2
- 6
Mistral 7B full kv cache out of memory
#11 opened by monster119120 - 8
Llama3-8B model url
#8 opened by monster119120 - 1
question about case selection in observations
#10 opened by Cooperx521 - 3
confused about some code
#6 opened by bohr - 1
correct transformers version
#7 opened by monster119120 - 2
mistral7B运行错误
#9 opened by monster119120 - 4