issues
search
ModelTC
/
llmc
[EMNLP 2024 Industry Track] This is the official PyTorch implementation of "LLMC: Benchmarking Large Language Model Quantization with a Versatile Compression Toolkit".
https://arxiv.org/abs/2405.06001
Apache License 2.0
328
stars
36
forks
source link
issues
Newest
Newest
Most commented
Recently updated
Oldest
Least commented
Least recently updated
Add KV cache quantization.
#233
gushiqiao
closed
7 hours ago
0
update multi-modal preprocess
#232
helloyongyang
closed
1 day ago
0
support audio-img-txt models and audio_img_txt calib data
#231
helloyongyang
closed
1 day ago
0
modify qwen and mixtral
#230
MercuryB1
closed
1 day ago
0
support flash-attention in dockerfile
#229
helloyongyang
closed
3 days ago
0
Fix bugs
#228
gushiqiao
closed
3 days ago
0
add vlm config and fix catch for qwen2vl
#227
chengtao-lv
closed
3 days ago
0
add audio-language model quantization config
#226
helloyongyang
closed
4 days ago
0
support qwen2audio model
#225
helloyongyang
closed
4 days ago
0
support use_cpu_to_save_cuda_mem_for_catcher for vlm quantization
#224
helloyongyang
closed
4 days ago
0
update vlm
#223
chengtao-lv
closed
5 days ago
0
support chatglm4v model and llava support img-txt txt calib data when…
#222
helloyongyang
closed
6 days ago
0
量化internlm2-chat-1_8b后，使用vllm推理时报错
#221
baisesj
closed
1 day ago
1
Fix sglang bugs
#220
gushiqiao
closed
6 days ago
0
add do_trans in config & remove language catcher & support chaglm
#219
helloyongyang
closed
1 week ago
0
update subset_transform
#218
helloyongyang
closed
1 week ago
0
Fix bugs
#217
llmc-reviewer
closed
1 week ago
0
Update readme
#216
gushiqiao
closed
1 week ago
0
Fix bugs
#215
llmc-reviewer
closed
1 week ago
0
update vlm models
#214
helloyongyang
closed
1 week ago
0
support add_answer for vlm models
#213
helloyongyang
closed
1 week ago
0
update models
#212
helloyongyang
closed
1 week ago
0
update qwen2vl model
#211
helloyongyang
closed
1 week ago
0
Update features
#210
gushiqiao
closed
1 week ago
0
Fix gptq bug
#209
llmc-reviewer
closed
1 week ago
0
update llava model
#208
helloyongyang
closed
1 week ago
0
update internvl2 model
#207
helloyongyang
closed
1 week ago
0
move tokenizer to BaseModel
#206
helloyongyang
closed
1 week ago
0
fix ci
#205
helloyongyang
closed
1 week ago
0
Support deepseekv2 quarot
#204
llmc-reviewer
closed
1 week ago
0
remove qwenvl
#203
helloyongyang
closed
1 week ago
0
update model
#202
helloyongyang
closed
1 week ago
0
md add introduce of vit, vlm,img dataset and img-txt dataset
#201
SmudgedWings
closed
1 week ago
0
add gptq check for ci
#200
SmudgedWings
closed
1 week ago
0
support quarot for VLM
#199
helloyongyang
closed
1 week ago
0
fix internvl2 eval MME
#198
helloyongyang
closed
1 week ago
0
update vlm
#197
helloyongyang
closed
1 week ago
0
update eval and support internvl for MME eval
#196
helloyongyang
closed
1 week ago
0
update ddp
#195
helloyongyang
closed
1 week ago
0
Dev
#194
helloyongyang
closed
1 week ago
0
update internvl2
#193
helloyongyang
closed
1 week ago
0
support cu124 dockerfile
#192
helloyongyang
closed
1 week ago
0
Update smoothquant.py
#191
gushiqiao
closed
1 week ago
0
support internvl2 multi imgs and single txt with bs=1
#190
helloyongyang
closed
1 week ago
0
support MME eval & naive quant for VLM
#189
helloyongyang
closed
2 weeks ago
0
Vlm
#188
gushiqiao
closed
2 weeks ago
0
Vlm
#187
gushiqiao
closed
2 weeks ago
0
update vlm
#186
gushiqiao
closed
2 weeks ago
0
Fix dp bugs
#185
llmc-reviewer
closed
2 weeks ago
0
Fix running average scales
#184
gushiqiao
closed
2 weeks ago
0
Next