TJian eaa92d4437 [ROCm] [Feature] [Doc] [Dockerfile] [BugFix] Support Per-Token-Activation Per-Channel-Weight FP8 Quantization Inferencing (#12501)

2025-02-07 08:13:43 -08:00

..

compressed_tensors

Add: Support for Sparse24Bitmask Compressed Models

2025-02-05 13:30:43 -08:00

kernels

[Misc] Add SPDX-License-Identifier headers to python source files (#12628)

2025-02-02 11:58:18 -08:00

quark

[Model][Quant] Fix GLM, Fix fused module mappings for quantization (#12634)

2025-02-05 05:32:06 +00:00

utils

[ROCm] [Feature] [Doc] [Dockerfile] [BugFix] Support Per-Token-Activation Per-Channel-Weight FP8 Quantization Inferencing (#12501)

2025-02-07 08:13:43 -08:00

__init__.py

[ROCm] [Feature] [Doc] [Dockerfile] [BugFix] Support Per-Token-Activation Per-Channel-Weight FP8 Quantization Inferencing (#12501)

2025-02-07 08:13:43 -08:00

aqlm.py

[Misc] Add SPDX-License-Identifier headers to python source files (#12628)

2025-02-02 11:58:18 -08:00

awq_marlin.py

[Misc] Add SPDX-License-Identifier headers to python source files (#12628)

2025-02-02 11:58:18 -08:00

awq_triton.py

[Misc] Add SPDX-License-Identifier headers to python source files (#12628)

2025-02-02 11:58:18 -08:00

awq.py

[Misc] Add SPDX-License-Identifier headers to python source files (#12628)

2025-02-02 11:58:18 -08:00

base_config.py

[Model][Quant] Fix GLM, Fix fused module mappings for quantization (#12634)

2025-02-05 05:32:06 +00:00

bitsandbytes.py

[Misc] Add SPDX-License-Identifier headers to python source files (#12628)

2025-02-02 11:58:18 -08:00

deepspeedfp.py

[Misc] Add SPDX-License-Identifier headers to python source files (#12628)

2025-02-02 11:58:18 -08:00

experts_int8.py

[Misc] Add SPDX-License-Identifier headers to python source files (#12628)

2025-02-02 11:58:18 -08:00

fbgemm_fp8.py

[Misc] Add SPDX-License-Identifier headers to python source files (#12628)

2025-02-02 11:58:18 -08:00

fp8.py

[Misc] Add SPDX-License-Identifier headers to python source files (#12628)

2025-02-02 11:58:18 -08:00

gguf.py

[Misc] Add SPDX-License-Identifier headers to python source files (#12628)

2025-02-02 11:58:18 -08:00

gptq_marlin_24.py

[Misc] Add SPDX-License-Identifier headers to python source files (#12628)

2025-02-02 11:58:18 -08:00

gptq_marlin.py

[Misc] Update w2 scale loading for GPTQMarlinMoE (#12757)

2025-02-06 01:02:14 -08:00

gptq.py

[Misc] Add SPDX-License-Identifier headers to python source files (#12628)

2025-02-02 11:58:18 -08:00

hqq_marlin.py

[Misc] Add SPDX-License-Identifier headers to python source files (#12628)

2025-02-02 11:58:18 -08:00

ipex_quant.py

[Misc] Add SPDX-License-Identifier headers to python source files (#12628)

2025-02-02 11:58:18 -08:00

kv_cache.py

[Misc] Add SPDX-License-Identifier headers to python source files (#12628)

2025-02-02 11:58:18 -08:00

marlin.py

[Misc] Add SPDX-License-Identifier headers to python source files (#12628)

2025-02-02 11:58:18 -08:00

modelopt.py

[Misc] Add SPDX-License-Identifier headers to python source files (#12628)

2025-02-02 11:58:18 -08:00

moe_wna16.py

Fix for attention layers to remain unquantized during moe_wn16 quant (#12570)

2025-02-03 13:46:19 +08:00

neuron_quant.py

[Misc] Add SPDX-License-Identifier headers to python source files (#12628)

2025-02-02 11:58:18 -08:00

ptpc_fp8.py

[ROCm] [Feature] [Doc] [Dockerfile] [BugFix] Support Per-Token-Activation Per-Channel-Weight FP8 Quantization Inferencing (#12501)

2025-02-07 08:13:43 -08:00

qqq.py

[Misc] Add SPDX-License-Identifier headers to python source files (#12628)

2025-02-02 11:58:18 -08:00

schema.py

[Misc] Add SPDX-License-Identifier headers to python source files (#12628)

2025-02-02 11:58:18 -08:00

tpu_int8.py

[Misc] Add SPDX-License-Identifier headers to python source files (#12628)

2025-02-02 11:58:18 -08:00