| .. |
|
gguf_utils
|
9d81716bfd
[v0.5.3] Release Candidate (#388)
|
10 kuukautta sitten |
|
__init__.py
|
f22b700ee4
feat: marlin kernels for GPTQ (#547)
|
8 kuukautta sitten |
|
aqlm.py
|
b178ae4b4a
chore: generalize linear_method to be quant_method (#540)
|
8 kuukautta sitten |
|
awq.py
|
b178ae4b4a
chore: generalize linear_method to be quant_method (#540)
|
8 kuukautta sitten |
|
base_config.py
|
b178ae4b4a
chore: generalize linear_method to be quant_method (#540)
|
8 kuukautta sitten |
|
bitsandbytes.py
|
b178ae4b4a
chore: generalize linear_method to be quant_method (#540)
|
8 kuukautta sitten |
|
eetq.py
|
b178ae4b4a
chore: generalize linear_method to be quant_method (#540)
|
8 kuukautta sitten |
|
exl2.py
|
b178ae4b4a
chore: generalize linear_method to be quant_method (#540)
|
8 kuukautta sitten |
|
fp8.py
|
36660b55c2
chore: mixtral fp8 w/ static scales (#542)
|
8 kuukautta sitten |
|
gguf.py
|
b178ae4b4a
chore: generalize linear_method to be quant_method (#540)
|
8 kuukautta sitten |
|
gptq.py
|
b178ae4b4a
chore: generalize linear_method to be quant_method (#540)
|
8 kuukautta sitten |
|
gptq_marlin.py
|
ac5b4b6aa7
broadcast metadata through cpu
|
8 kuukautta sitten |
|
hadamard.safetensors
|
9d81716bfd
[v0.5.3] Release Candidate (#388)
|
10 kuukautta sitten |
|
marlin.py
|
b178ae4b4a
chore: generalize linear_method to be quant_method (#540)
|
8 kuukautta sitten |
|
quip.py
|
b178ae4b4a
chore: generalize linear_method to be quant_method (#540)
|
8 kuukautta sitten |
|
quip_utils.py
|
9d81716bfd
[v0.5.3] Release Candidate (#388)
|
10 kuukautta sitten |
|
schema.py
|
9d81716bfd
[v0.5.3] Release Candidate (#388)
|
10 kuukautta sitten |
|
squeezellm.py
|
b178ae4b4a
chore: generalize linear_method to be quant_method (#540)
|
8 kuukautta sitten |
AlpinDale
ac5b4b6aa7
broadcast metadata through cpu