.. |
compressed_tensors
|
f1e1d0bd3d
feat: introduce `BaseAphroditeParameter` (#646)
|
4 miesięcy temu |
gguf_utils
|
9d81716bfd
[v0.5.3] Release Candidate (#388)
|
8 miesięcy temu |
utils
|
3170c0d4c6
fix: GPTQ/AWQ on Colab (#655)
|
4 miesięcy temu |
__init__.py
|
3f49a55f82
feat: add INT8 W8A16 quant for TPU (#663)
|
4 miesięcy temu |
aqlm.py
|
f1d0b77c92
[0.6.0] Release Candidate (#481)
|
4 miesięcy temu |
autoquant.py
|
f1d0b77c92
[0.6.0] Release Candidate (#481)
|
4 miesięcy temu |
awq.py
|
f1d0b77c92
[0.6.0] Release Candidate (#481)
|
4 miesięcy temu |
awq_marlin.py
|
3170c0d4c6
fix: GPTQ/AWQ on Colab (#655)
|
4 miesięcy temu |
base_config.py
|
f1d0b77c92
[0.6.0] Release Candidate (#481)
|
4 miesięcy temu |
bitsandbytes.py
|
f1d0b77c92
[0.6.0] Release Candidate (#481)
|
4 miesięcy temu |
deepspeedfp.py
|
f1d0b77c92
[0.6.0] Release Candidate (#481)
|
4 miesięcy temu |
eetq.py
|
f1d0b77c92
[0.6.0] Release Candidate (#481)
|
4 miesięcy temu |
exl2.py
|
f1d0b77c92
[0.6.0] Release Candidate (#481)
|
4 miesięcy temu |
fbgemm_fp8.py
|
f1d0b77c92
[0.6.0] Release Candidate (#481)
|
4 miesięcy temu |
fp8.py
|
f1d0b77c92
[0.6.0] Release Candidate (#481)
|
4 miesięcy temu |
gguf.py
|
f1d0b77c92
[0.6.0] Release Candidate (#481)
|
4 miesięcy temu |
gptq.py
|
f1d0b77c92
[0.6.0] Release Candidate (#481)
|
4 miesięcy temu |
gptq_marlin.py
|
3170c0d4c6
fix: GPTQ/AWQ on Colab (#655)
|
4 miesięcy temu |
gptq_marlin_24.py
|
f1d0b77c92
[0.6.0] Release Candidate (#481)
|
4 miesięcy temu |
hadamard.safetensors
|
9d81716bfd
[v0.5.3] Release Candidate (#388)
|
8 miesięcy temu |
kv_cache.py
|
f1d0b77c92
[0.6.0] Release Candidate (#481)
|
4 miesięcy temu |
marlin.py
|
f1d0b77c92
[0.6.0] Release Candidate (#481)
|
4 miesięcy temu |
qqq.py
|
f1d0b77c92
[0.6.0] Release Candidate (#481)
|
4 miesięcy temu |
quip.py
|
f1d0b77c92
[0.6.0] Release Candidate (#481)
|
4 miesięcy temu |
quip_utils.py
|
9d81716bfd
[v0.5.3] Release Candidate (#388)
|
8 miesięcy temu |
schema.py
|
9d81716bfd
[v0.5.3] Release Candidate (#388)
|
8 miesięcy temu |
squeezellm.py
|
f1d0b77c92
[0.6.0] Release Candidate (#481)
|
4 miesięcy temu |
tpu_int8.py
|
3f49a55f82
feat: add INT8 W8A16 quant for TPU (#663)
|
4 miesięcy temu |