vLLM/vllm/model_executor/layers/quantization at d2740fafbf2527f4026863854bf1aeaa383c1a8e - vLLM

compressed_tensors

[ROCm][FEAT] Fuse DeepSeek shared experts into AITER fused_moe ops (#24097 )

2025-10-16 10:41:34 +08:00

kernels

Update Optional[x] -> x | None and Union[x, y] to x | y (#26633 )

2025-10-12 09:51:31 -07:00

quark

[torch.compile] Unwrap fused_marlin_moe custom op (#26739 )

2025-10-14 02:22:16 +00:00

utils

support flashinfer_fp4 moe for 5090 gpu (#26669 )

2025-10-15 15:06:47 -04:00

__init__.py

[Transform] [Quantization] Add QuTLASS support to vLLM (#24440 )

2025-10-10 09:43:40 -07:00

auto_round.py

[Feature][Quantization] auto_round format add support for regex (#24024 )

2025-10-14 03:03:16 +00:00

awq_marlin.py

[torch.compile] Unwrap fused_marlin_moe custom op (#26739 )

2025-10-14 02:22:16 +00:00

awq_triton.py

Convert formatting to use ruff instead of yapf + isort (#26247 )

2025-10-05 07:06:22 -07:00

awq.py

Update Optional[x] -> x | None and Union[x, y] to x | y (#26633 )

2025-10-12 09:51:31 -07:00

base_config.py

Update Optional[x] -> x | None and Union[x, y] to x | y (#26633 )

2025-10-12 09:51:31 -07:00

bitblas.py

Update Optional[x] -> x | None and Union[x, y] to x | y (#26633 )

2025-10-12 09:51:31 -07:00

bitsandbytes.py

Update Optional[x] -> x | None and Union[x, y] to x | y (#26633 )

2025-10-12 09:51:31 -07:00

deepspeedfp.py

Update Optional[x] -> x | None and Union[x, y] to x | y (#26633 )

2025-10-12 09:51:31 -07:00

experts_int8.py

Update Optional[x] -> x | None and Union[x, y] to x | y (#26633 )

2025-10-12 09:51:31 -07:00

fbgemm_fp8.py

Update Optional[x] -> x | None and Union[x, y] to x | y (#26633 )

2025-10-12 09:51:31 -07:00

fp8.py

Deepseek-v3 Batch Invariant on 8xH100 (#26609 )

2025-10-15 22:06:02 -07:00

fp_quant.py

Update Optional[x] -> x | None and Union[x, y] to x | y (#26633 )

2025-10-12 09:51:31 -07:00

gguf.py

Update Optional[x] -> x | None and Union[x, y] to x | y (#26633 )

2025-10-12 09:51:31 -07:00

gptq_bitblas.py

Update Optional[x] -> x | None and Union[x, y] to x | y (#26633 )

2025-10-12 09:51:31 -07:00

gptq_marlin_24.py

Update Optional[x] -> x | None and Union[x, y] to x | y (#26633 )

2025-10-12 09:51:31 -07:00

gptq_marlin.py

[Chore] Separate out vllm.utils.collections (#26990 )

2025-10-16 08:35:35 +00:00

gptq.py

[Chore] Separate out vllm.utils.collections (#26990 )

2025-10-16 08:35:35 +00:00

hqq_marlin.py

Update Optional[x] -> x | None and Union[x, y] to x | y (#26633 )

2025-10-12 09:51:31 -07:00

inc.py

Convert formatting to use ruff instead of yapf + isort (#26247 )

2025-10-05 07:06:22 -07:00

input_quant_fp8.py

Update Optional[x] -> x | None and Union[x, y] to x | y (#26633 )

2025-10-12 09:51:31 -07:00

ipex_quant.py

Update Optional[x] -> x | None and Union[x, y] to x | y (#26633 )

2025-10-12 09:51:31 -07:00

kv_cache.py

Convert formatting to use ruff instead of yapf + isort (#26247 )

2025-10-05 07:06:22 -07:00

modelopt.py

[NVIDIA] Add support for cudnn fp4 gemm via flashinfer (#26107 )

2025-10-15 13:53:00 -04:00

moe_wna16.py

Update Optional[x] -> x | None and Union[x, y] to x | y (#26633 )

2025-10-12 09:51:31 -07:00

mxfp4.py

[torch.compile] Unwrap fused_marlin_moe custom op (#26739 )

2025-10-14 02:22:16 +00:00

petit.py

Update Optional[x] -> x | None and Union[x, y] to x | y (#26633 )

2025-10-12 09:51:31 -07:00

ptpc_fp8.py

Update Optional[x] -> x | None and Union[x, y] to x | y (#26633 )

2025-10-12 09:51:31 -07:00

qutlass_utils.py

[Transform] [Quantization] Add QuTLASS support to vLLM (#24440 )

2025-10-10 09:43:40 -07:00

rtn.py

[CI Failure] Fix torchao dep failure for Quantization Test (#26824 )

2025-10-14 16:41:43 -07:00

schema.py

Update Optional[x] -> x | None and Union[x, y] to x | y (#26633 )

2025-10-12 09:51:31 -07:00

torchao.py

Update Optional[x] -> x | None and Union[x, y] to x | y (#26633 )

2025-10-12 09:51:31 -07:00

tpu_int8.py

Update Optional[x] -> x | None and Union[x, y] to x | y (#26633 )

2025-10-12 09:51:31 -07:00