.. |
aqlm
|
156f577f79
feat: switch from `PYBIND11_MODULE` to `TORCH_LIBRARY` (#569)
|
преди 7 месеца |
autoquant
|
156f577f79
feat: switch from `PYBIND11_MODULE` to `TORCH_LIBRARY` (#569)
|
преди 7 месеца |
awq
|
156f577f79
feat: switch from `PYBIND11_MODULE` to `TORCH_LIBRARY` (#569)
|
преди 7 месеца |
compressed_tensors
|
156f577f79
feat: switch from `PYBIND11_MODULE` to `TORCH_LIBRARY` (#569)
|
преди 7 месеца |
cutlass_w8a8
|
b03b4d4c8c
fix: compute cutlass 3.x epilogues in fp32 instead of 16
|
преди 7 месеца |
exl2
|
156f577f79
feat: switch from `PYBIND11_MODULE` to `TORCH_LIBRARY` (#569)
|
преди 7 месеца |
fp8
|
ad24e74a99
feat: FP8 weight-only quantization support for Ampere GPUs
|
преди 6 месеца |
gguf
|
9d81716bfd
[v0.5.3] Release Candidate (#388)
|
преди 10 месеца |
gptq
|
156f577f79
feat: switch from `PYBIND11_MODULE` to `TORCH_LIBRARY` (#569)
|
преди 7 месеца |
gptq_marlin
|
156f577f79
feat: switch from `PYBIND11_MODULE` to `TORCH_LIBRARY` (#569)
|
преди 7 месеца |
int8_kvcache
|
9810daa699
feat: INT8 KV Cache (#298)
|
преди 1 година |
marlin
|
1587fab5de
fix: cuda version check for mma warning suppression
|
преди 7 месеца |
quip
|
156f577f79
feat: switch from `PYBIND11_MODULE` to `TORCH_LIBRARY` (#569)
|
преди 7 месеца |
squeezellm
|
156f577f79
feat: switch from `PYBIND11_MODULE` to `TORCH_LIBRARY` (#569)
|
преди 7 месеца |
quant_ops.h
|
ad24e74a99
feat: FP8 weight-only quantization support for Ampere GPUs
|
преди 6 месеца |