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
326
stars
34
forks
source link
issues
Newest
Newest
Most commented
Recently updated
Oldest
Least commented
Least recently updated
Discord link brroken
#176
TweedBeetle
closed
3 weeks ago
1
How to Quantize with SpinQuant and Export to VLLM
#175
TweedBeetle
closed
3 weeks ago
6
Support deepseek attn qunatization and recon auto clip
#174
gushiqiao
closed
3 weeks ago
0
Fix bug
#173
llmc-reviewer
closed
3 weeks ago
0
mistral model support quarot
#172
helloyongyang
closed
3 weeks ago
0
Fix bugs
#171
gushiqiao
closed
3 weeks ago
0
Add support for static quantization, attention quantization, and mult…
#170
gushiqiao
closed
3 weeks ago
0
support Mllama(llama3.2) and update vit
#169
SmudgedWings
closed
3 weeks ago
0
support Mllama(llama3.2) and update vit
#168
SmudgedWings
closed
3 weeks ago
0
update
#167
helloyongyang
closed
3 weeks ago
0
chatglm series model support.
#166
simplew2011
closed
3 weeks ago
1
update readme
#165
Harahan
closed
3 weeks ago
0
Update quant.py
#164
gushiqiao
closed
3 weeks ago
0
BUG: Mixed-precision configuration not working with STATIC quantization
#163
sasha-hailo
opened
4 weeks ago
8
Update quant.py
#162
yhhhli
closed
3 weeks ago
1
PPL results for AWQ is not correct?
#161
yc2367
closed
4 weeks ago
2
Add Tessreaq method
#160
gushiqiao
closed
1 month ago
0
update dockerfile
#159
helloyongyang
closed
1 month ago
0
fail to run awq on qwen2-7B
#158
Muuut
closed
1 month ago
2
Add dockerfile
#157
helloyongyang
closed
1 month ago
0
fix collect_first_block_input
#156
helloyongyang
closed
1 month ago
0
support auto get padding side
#155
helloyongyang
closed
1 month ago
0
add try except for InternVL2
#154
helloyongyang
closed
1 month ago
0
update
#153
helloyongyang
closed
1 month ago
0
support padding mask when calib bs >= 1
#152
helloyongyang
closed
1 month ago
0
change some info to warning
#151
helloyongyang
closed
1 month ago
0
fix preprocess bug
#150
helloyongyang
closed
1 month ago
0
support padding mask for vlm
#149
helloyongyang
closed
1 month ago
0
KV cache / post-RoPE rotation & quantization in QuaRot
#148
sasha-hailo
closed
1 month ago
5
Dev spinquant
#147
gushiqiao
closed
1 month ago
0
Dev spinquant
#146
gushiqiao
closed
1 month ago
0
support padding mask for auto clip
#145
helloyongyang
closed
1 month ago
0
Fix vit calib data bug
#144
gushiqiao
closed
1 month ago
0
add config
#143
helloyongyang
closed
1 month ago
0
Dev2
#142
helloyongyang
closed
1 month ago
0
support padding mask
#141
helloyongyang
closed
1 month ago
0
Update mse quant
#140
gushiqiao
closed
1 month ago
0
fix bugs for rotary_emb
#139
helloyongyang
closed
1 month ago
0
Update float-quant settings
#138
gushiqiao
closed
1 month ago
0
update for mask preproc
#137
helloyongyang
closed
1 month ago
0
llmc可以支持smoothqaunt的w8a8在trt-llm后端推理吗？
#136
GuangyanZhang
closed
1 month ago
2
Refine Float-quant
#135
gushiqiao
closed
1 month ago
0
add deepseekv2
#134
MercuryB1
closed
1 month ago
0
vit support awq
#133
SmudgedWings
closed
1 month ago
0
add qwen2 moe
#132
MercuryB1
closed
1 month ago
0
aw
#131
SmudgedWings
closed
1 month ago
0
add qwen2moe
#130
MercuryB1
closed
1 month ago
0
Swap
#129
SmudgedWings
closed
1 month ago
0
update readme
#128
helloyongyang
closed
1 month ago
0
update requirements
#127
helloyongyang
closed
1 month ago
0
Previous
Next