.. |
compressed_tensors
|
93bc863591
feat: Machete Kernels for Hopper GPUs (#842)
|
пре 1 месец |
gguf_utils
|
8a71788372
Add OLMoE (#772)
|
пре 2 месеци |
kernels
|
93bc863591
feat: Machete Kernels for Hopper GPUs (#842)
|
пре 1 месец |
utils
|
93bc863591
feat: Machete Kernels for Hopper GPUs (#842)
|
пре 1 месец |
__init__.py
|
f98e7b2f8c
feat: add HQQ quantization support (#795)
|
пре 2 месеци |
aqlm.py
|
ccbda97416
fix: types in AQLM and GGUF for dynamo support (#736)
|
пре 3 месеци |
autoquant.py
|
f1d0b77c92
[0.6.0] Release Candidate (#481)
|
пре 4 месеци |
awq.py
|
edec2e9a9e
feat: migrate awq and awq_marlin to AphroditeParameter (#702)
|
пре 4 месеци |
awq_marlin.py
|
93bc863591
feat: Machete Kernels for Hopper GPUs (#842)
|
пре 1 месец |
base_config.py
|
f1d0b77c92
[0.6.0] Release Candidate (#481)
|
пре 4 месеци |
bitsandbytes.py
|
f1d0b77c92
[0.6.0] Release Candidate (#481)
|
пре 4 месеци |
deepspeedfp.py
|
f1d0b77c92
[0.6.0] Release Candidate (#481)
|
пре 4 месеци |
eetq.py
|
f1d0b77c92
[0.6.0] Release Candidate (#481)
|
пре 4 месеци |
exl2.py
|
f1d0b77c92
[0.6.0] Release Candidate (#481)
|
пре 4 месеци |
experts_int8.py
|
d34e083c48
feat: add experts_int8 support (#730)
|
пре 3 месеци |
fbgemm_fp8.py
|
f1d0b77c92
[0.6.0] Release Candidate (#481)
|
пре 4 месеци |
fp6.py
|
73177656ed
feat: quant_llm support (#755)
|
пре 3 месеци |
fp8.py
|
22a4cd4595
core: fix spec decode metrics and envs circular import (#889)
|
пре 3 недеља |
gguf.py
|
f1d0b77c92
[0.6.0] Release Candidate (#481)
|
пре 4 месеци |
gptq.py
|
ccbda97416
fix: types in AQLM and GGUF for dynamo support (#736)
|
пре 3 месеци |
gptq_marlin.py
|
93bc863591
feat: Machete Kernels for Hopper GPUs (#842)
|
пре 1 месец |
gptq_marlin_24.py
|
f1d0b77c92
[0.6.0] Release Candidate (#481)
|
пре 4 месеци |
hadamard.safetensors
|
9d81716bfd
[v0.5.3] Release Candidate (#388)
|
пре 8 месеци |
hqq_marlin.py
|
f98e7b2f8c
feat: add HQQ quantization support (#795)
|
пре 2 месеци |
kv_cache.py
|
f1d0b77c92
[0.6.0] Release Candidate (#481)
|
пре 4 месеци |
marlin.py
|
f1d0b77c92
[0.6.0] Release Candidate (#481)
|
пре 4 месеци |
qqq.py
|
f1d0b77c92
[0.6.0] Release Candidate (#481)
|
пре 4 месеци |
quip.py
|
f1d0b77c92
[0.6.0] Release Candidate (#481)
|
пре 4 месеци |
quip_utils.py
|
8a71788372
Add OLMoE (#772)
|
пре 2 месеци |
schema.py
|
9d81716bfd
[v0.5.3] Release Candidate (#388)
|
пре 8 месеци |
squeezellm.py
|
f1d0b77c92
[0.6.0] Release Candidate (#481)
|
пре 4 месеци |
tpu_int8.py
|
3f49a55f82
feat: add INT8 W8A16 quant for TPU (#663)
|
пре 4 месеци |