vLLM/vllm/model_executor/layers/quantization at 5caaeb714ce3fd08de9c2e87848b4825bb4b676d - vLLM

compressed_tensors

[fix]: add Arm 4bit fused moe support (#23809 )

2025-09-24 01:32:22 +00:00

kernels

Remove redundant mutates_args and dispatch_key for direct_register_custom_op (#25512 )

2025-09-23 22:48:40 +00:00

quark

[Kernel] Delegate construction of FusedMoEQuantConfig to FusedMoEMethodBase subclasses (#22537 )

2025-09-17 17:43:31 -06:00

utils

[ROCm] Small functional changes for gptoss (#25201 )

2025-09-23 23:39:50 +00:00

__init__.py

[V0 deprecation] Deprecate V0 Neuron backend (#21159 )

2025-09-06 16:15:18 -07:00

auto_round.py

Fix: Correct FusedMoE layer reference in auto_round quantization (#24818 )

2025-09-19 20:44:24 +00:00

awq_marlin.py

[Kernel] Delegate construction of FusedMoEQuantConfig to FusedMoEMethodBase subclasses (#22537 )

2025-09-17 17:43:31 -06:00

awq_triton.py

[Doc]: fix typos in Python comments (#24173 )

2025-09-04 08:52:17 -07:00

awq.py

[Kernels] Clean up FusedMoeMethodBase and modular kernel setup. Remove extra arguments from modular kernel methods. (#22035 )

2025-08-15 14:46:00 -04:00

base_config.py

[Doc]: fix typos in Python comments (#24173 )

2025-09-04 08:52:17 -07:00

bitblas.py

[Docs] Fix warnings in mkdocs build (continued) (#24092 )

2025-09-10 06:23:28 -07:00

bitsandbytes.py

[Kernel] Delegate construction of FusedMoEQuantConfig to FusedMoEMethodBase subclasses (#22537 )

2025-09-17 17:43:31 -06:00

deepgemm.py

Remove redundant mutates_args and dispatch_key for direct_register_custom_op (#25512 )

2025-09-23 22:48:40 +00:00

deepspeedfp.py

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

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

experts_int8.py

[Kernel] Delegate construction of FusedMoEQuantConfig to FusedMoEMethodBase subclasses (#22537 )

2025-09-17 17:43:31 -06:00

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

[Performance] Move apply_w8a8_block_fp8_linear to an op class (#24666 )

2025-09-23 12:03:10 -07:00

gguf.py

Remove redundant mutates_args and dispatch_key for direct_register_custom_op (#25512 )

2025-09-23 22:48:40 +00:00

gptq_bitblas.py

[Docs] Fix warnings in mkdocs build (continued) (#24092 )

2025-09-10 06:23:28 -07:00

gptq_marlin_24.py

[Misc] Add SPDX-FileCopyrightText (#19100 )

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

gptq_marlin.py

[Kernel] Delegate construction of FusedMoEQuantConfig to FusedMoEMethodBase subclasses (#22537 )

2025-09-17 17:43:31 -06:00

gptq.py

[BUGFIX] GPTQ quantization compatibility for Qwen3 MOE models (AutoGPTQ and AutoRound-GPTQ) (#23994 )

2025-09-01 03:33:40 +00:00

hqq_marlin.py

[Kernel] [Quantization] Add MXFP4 and bias support for marlin kernel (#22428 )

2025-08-14 11:23:22 -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

[Performance] Move apply_w8a8_block_fp8_linear to an op class (#24666 )

2025-09-23 12:03:10 -07:00

ipex_quant.py

[Kernel] Delegate construction of FusedMoEQuantConfig to FusedMoEMethodBase subclasses (#22537 )

2025-09-17 17:43:31 -06:00

kv_cache.py

fp8 kv cache support fix for torch.compile (#22758 )

2025-09-16 21:27:11 +00:00

modelopt.py

Enable modelopt gemma3 nvfp4/fp8, make workflow more robust (#22771 )

2025-09-19 22:40:33 +00:00

moe_wna16.py

[Kernel] Delegate construction of FusedMoEQuantConfig to FusedMoEMethodBase subclasses (#22537 )

2025-09-17 17:43:31 -06:00

mxfp4.py

[ROCm] Small functional changes for gptoss (#25201 )

2025-09-23 23:39:50 +00:00

petit.py

Quantization: support FP4 quantized models on AMD CDNA2/CDNA3 GPUs (#22527 )

2025-08-22 20:53:21 -06:00

ptpc_fp8.py

[Misc] Removed force_fp8_e4m3fnuz from FP8LinearOp (#23725 )

2025-09-04 09:25:40 -04:00

rtn.py

[Kernel] Delegate construction of FusedMoEQuantConfig to FusedMoEMethodBase subclasses (#22537 )

2025-09-17 17:43:31 -06:00

schema.py

[Misc] Add SPDX-FileCopyrightText (#19100 )

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

torchao.py

[Docs] Fix warnings in mkdocs build (continued) (#24740 )

2025-09-12 06:43:15 -07:00

tpu_int8.py

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

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