vLLM/vllm/model_executor/layers/quantization at 80bb1e8afe950342e93b7262e7bf25eb6d29b287 - vLLM

compressed_tensors

Support Tensorrt-LLM MoE fp4 for low-latency (#21331 )

2025-08-07 19:18:22 -07:00

kernels

[Bugfix] Add proper comparison for package versions (#22314 )

2025-08-06 20:31:03 -07:00

quark

[Perf][fp8] Use CustomOp abstraction for fp8 quant for better perf (#19830 )

2025-07-11 04:56:28 +00:00

utils

[gpt-oss] Fix mxfp4 support (#22700 )

2025-08-11 21:22:26 -07:00

__init__.py

[gpt-oss] flashinfer mxfp4 (#22339 )

2025-08-06 12:37:27 -07:00

aqlm.py

[Misc] Add SPDX-FileCopyrightText (#19100 )

2025-06-03 11:20:17 -07:00

auto_round.py

[Bugfix]fix mixed bits and visual language model quantization in AutoRound (#21802 )

2025-07-29 07:26:31 -07:00

awq_marlin.py

Fix: AWQ Marlin get_quant_method does not recognize "modules_to_not_convert" (#21888 )

2025-08-12 02:03:53 -07:00

awq_triton.py

[Misc] Add SPDX-FileCopyrightText (#19100 )

2025-06-03 11:20:17 -07:00

awq.py

[Quantization] Improve AWQ logic (#19431 )

2025-06-12 11:02:11 +00:00

base_config.py

[Quant] [Bugfix] Fix quantization config matching with hf_to_vllm_mapper (#20046 )

2025-07-01 19:20:34 +09:00

bitblas.py

[Bugfix] Add proper comparison for package versions (#22314 )

2025-08-06 20:31:03 -07:00

bitsandbytes.py

[Bugfix] Add proper comparison for package versions (#22314 )

2025-08-06 20:31:03 -07:00

deepgemm.py

[Feature] Integrate SM100 DeepGEMM support (#20087 )

2025-07-10 20:18:05 -07:00

deepspeedfp.py

[Bugfix] Add proper comparison for package versions (#22314 )

2025-08-06 20:31:03 -07:00

experts_int8.py

[Feature] Expert Parallelism Load Balancer (EPLB) (#18343 )

2025-06-26 15:30:21 -07:00

fbgemm_fp8.py

[Perf][fp8] Use CustomOp abstraction for fp8 quant for better perf (#19830 )

2025-07-11 04:56:28 +00:00

fp8.py

[Feature] Add VLLM_USE_DEEP_GEMM_E8M0 Env to Control E8M0 Scale (#21968 )

2025-08-11 09:39:08 -07:00

gguf.py

[Feature] Expert Parallelism Load Balancer (EPLB) (#18343 )

2025-06-26 15:30:21 -07:00

gptq_bitblas.py

[Bugfix] Add proper comparison for package versions (#22314 )

2025-08-06 20:31:03 -07:00

gptq_marlin_24.py

[Misc] Add SPDX-FileCopyrightText (#19100 )

2025-06-03 11:20:17 -07:00

gptq_marlin.py

Support Llama 4 for fused_marlin_moe (#20457 )

2025-07-04 07:55:10 +00:00

gptq.py

feat: Add Support GPTQ Quantization MOE on ROCM vllm serve (#21733 )

2025-08-01 21:12:19 -04:00

hqq_marlin.py

[Misc] Add SPDX-FileCopyrightText (#19100 )

2025-06-03 11:20:17 -07:00

inc.py

Support FP8 Quantization and Inference Run on Intel Gaudi (HPU) using INC (Intel Neural Compressor) (#12010 )

2025-07-16 15:33:41 -04:00

input_quant_fp8.py

[Perf][fp8] Use CustomOp abstraction for fp8 quant for better perf (#19830 )

2025-07-11 04:56:28 +00:00

ipex_quant.py

[Bugfix] Add proper comparison for package versions (#22314 )

2025-08-06 20:31:03 -07:00

kv_cache.py

[Misc] Add SPDX-FileCopyrightText (#19100 )

2025-06-03 11:20:17 -07:00

marlin.py

[Quant] [Bugfix] Fix quantization config matching with hf_to_vllm_mapper (#20046 )

2025-07-01 19:20:34 +09:00

modelopt.py

Support Tensorrt-LLM MoE fp4 for low-latency (#21331 )

2025-08-07 19:18:22 -07:00

moe_wna16.py

[Feature] Expert Parallelism Load Balancer (EPLB) (#18343 )

2025-06-26 15:30:21 -07:00

mxfp4.py

[gpt-oss] Enable gpt-oss on ampere (#22714 )

2025-08-12 03:21:44 -07:00

neuron_quant.py

[Misc] Add SPDX-FileCopyrightText (#19100 )

2025-06-03 11:20:17 -07:00

ptpc_fp8.py

[Perf][fp8] Use CustomOp abstraction for fp8 quant for better perf (#19830 )

2025-07-11 04:56:28 +00:00

qqq.py

[Misc] Add SPDX-FileCopyrightText (#19100 )

2025-06-03 11:20:17 -07:00

rtn.py

[Feature] Add support for MoE models in the calibration-free RTN-based quantization (#20766 )

2025-07-25 18:09:34 -07:00

schema.py

[Misc] Add SPDX-FileCopyrightText (#19100 )

2025-06-03 11:20:17 -07:00

torchao.py

[Quant] [Bugfix] Fix quantization config matching with hf_to_vllm_mapper (#20046 )

2025-07-01 19:20:34 +09:00

tpu_int8.py

[TPU] Add support for online w8a8 quantization (#22425 )

2025-08-08 23:12:54 -07:00