| .. |
|
compressed_tensors
|
93bc863591
feat: Machete Kernels for Hopper GPUs (#842)
|
1 mese fa |
|
gguf_utils
|
8a71788372
Add OLMoE (#772)
|
2 mesi fa |
|
kernels
|
93bc863591
feat: Machete Kernels for Hopper GPUs (#842)
|
1 mese fa |
|
utils
|
93bc863591
feat: Machete Kernels for Hopper GPUs (#842)
|
1 mese fa |
|
__init__.py
|
f98e7b2f8c
feat: add HQQ quantization support (#795)
|
2 mesi fa |
|
aqlm.py
|
ccbda97416
fix: types in AQLM and GGUF for dynamo support (#736)
|
3 mesi fa |
|
autoquant.py
|
f1d0b77c92
[0.6.0] Release Candidate (#481)
|
4 mesi fa |
|
awq.py
|
edec2e9a9e
feat: migrate awq and awq_marlin to AphroditeParameter (#702)
|
4 mesi fa |
|
awq_marlin.py
|
93bc863591
feat: Machete Kernels for Hopper GPUs (#842)
|
1 mese fa |
|
base_config.py
|
f1d0b77c92
[0.6.0] Release Candidate (#481)
|
4 mesi fa |
|
bitsandbytes.py
|
f1d0b77c92
[0.6.0] Release Candidate (#481)
|
4 mesi fa |
|
deepspeedfp.py
|
f1d0b77c92
[0.6.0] Release Candidate (#481)
|
4 mesi fa |
|
eetq.py
|
f1d0b77c92
[0.6.0] Release Candidate (#481)
|
4 mesi fa |
|
exl2.py
|
f1d0b77c92
[0.6.0] Release Candidate (#481)
|
4 mesi fa |
|
experts_int8.py
|
d34e083c48
feat: add experts_int8 support (#730)
|
3 mesi fa |
|
fbgemm_fp8.py
|
f1d0b77c92
[0.6.0] Release Candidate (#481)
|
4 mesi fa |
|
fp6.py
|
73177656ed
feat: quant_llm support (#755)
|
3 mesi fa |
|
fp8.py
|
d34e083c48
feat: add experts_int8 support (#730)
|
3 mesi fa |
|
gguf.py
|
f1d0b77c92
[0.6.0] Release Candidate (#481)
|
4 mesi fa |
|
gptq.py
|
ccbda97416
fix: types in AQLM and GGUF for dynamo support (#736)
|
3 mesi fa |
|
gptq_marlin.py
|
93bc863591
feat: Machete Kernels for Hopper GPUs (#842)
|
1 mese fa |
|
gptq_marlin_24.py
|
f1d0b77c92
[0.6.0] Release Candidate (#481)
|
4 mesi fa |
|
hadamard.safetensors
|
9d81716bfd
[v0.5.3] Release Candidate (#388)
|
8 mesi fa |
|
hqq_marlin.py
|
f98e7b2f8c
feat: add HQQ quantization support (#795)
|
2 mesi fa |
|
kv_cache.py
|
f1d0b77c92
[0.6.0] Release Candidate (#481)
|
4 mesi fa |
|
marlin.py
|
f1d0b77c92
[0.6.0] Release Candidate (#481)
|
4 mesi fa |
|
qqq.py
|
f1d0b77c92
[0.6.0] Release Candidate (#481)
|
4 mesi fa |
|
quip.py
|
f1d0b77c92
[0.6.0] Release Candidate (#481)
|
4 mesi fa |
|
quip_utils.py
|
8a71788372
Add OLMoE (#772)
|
2 mesi fa |
|
schema.py
|
9d81716bfd
[v0.5.3] Release Candidate (#388)
|
8 mesi fa |
|
squeezellm.py
|
f1d0b77c92
[0.6.0] Release Candidate (#481)
|
4 mesi fa |
|
tpu_int8.py
|
3f49a55f82
feat: add INT8 W8A16 quant for TPU (#663)
|
4 mesi fa |
AlpinDale
93bc863591
feat: Machete Kernels for Hopper GPUs (#842)