Michael Goin 28a6d5423d

[Bugfix] Fix Machete zero point issue for GPTQ models on SM90 (#21066) ...

Signed-off-by: mgoin <mgoin64@gmail.com>

2025-07-16 19:54:45 -07:00

..

compressed_tensors

[Bugfix] Correct per_act_token in CompressedTensorsW8A8Fp8MoECutlassM… (#20937)

2025-07-15 19:53:42 -07:00

kernels

[Bugfix] Fix Machete zero point issue for GPTQ models on SM90 (#21066)

2025-07-16 19:54:45 -07:00

quark

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

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

utils

[Doc] Remove duplicate docstring (#21012)

2025-07-15 20:09:13 -07:00

__init__.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

aqlm.py

[Misc] Add SPDX-FileCopyrightText (#19100)

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

auto_round.py

[Misc] Add SPDX-FileCopyrightText (#19100)

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

awq_marlin.py

Support Llama 4 for fused_marlin_moe (#20457)

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

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

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

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

bitsandbytes.py

Enabled BnB NF4 inference on Gaudi (#20172)

2025-07-14 20:26:08 -07:00

deepgemm.py

[Feature] Integrate SM100 DeepGEMM support (#20087)

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

deepspeedfp.py

[Misc] Add SPDX-FileCopyrightText (#19100)

2025-06-03 11:20:17 -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

[Bugfix] Fix incorrect dispatch for CutlassBlockScaledGroupedGemm and DeepGEMM (#20933)

2025-07-15 01:42:17 +00:00

gguf.py

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

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

gptq_bitblas.py

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

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

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

[Misc] Add SPDX-FileCopyrightText (#19100)

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

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

[CPU] Fix torch version in x86 CPU backend (#19258)

2025-06-26 03:34:47 -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

Enable ModelOpt Llama4 fp8 checkpoint deployment (#20419)

2025-07-11 23:07:16 -07:00

moe_wna16.py

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

2025-06-26 15:30:21 -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

[Misc] Add SPDX-FileCopyrightText (#20428)

2025-07-04 07:40:42 +00:00

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

[Misc] Add SPDX-FileCopyrightText (#19100)

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