Divakar Verma 6341d43043 [ROCm][Quantization] add quark w4a8 mxfp4_fp8 for LinearLayer (#35316) ...

Signed-off-by: Divakar Verma <divakar.verma@amd.com>

2026-03-13 19:44:24 +00:00

..

compressed_tensors

[UX] Only show FP4 Marlin fallback warning for w4a4 models (#36806)

2026-03-12 05:19:35 -04:00

quark

[ROCm][Quantization] add quark w4a8 mxfp4_fp8 for LinearLayer (#35316)

2026-03-13 19:44:24 +00:00

utils

[UX] Only show FP4 Marlin fallback warning for w4a4 models (#36806)

2026-03-12 05:19:35 -04:00

__init__.py

add mixed precision support for modelopt (#35047)

2026-02-26 21:56:24 +00:00

awq_marlin.py

…

awq_triton.py

…

awq.py

…

base_config.py

…

bitsandbytes.py

…

cpu_wna16.py

[Bugfix][CI] fix typos (#34934)

2026-03-05 17:05:46 +00:00

experts_int8.py

…

fbgemm_fp8.py

…

fp8.py

[MoE Refactor] Create MK for TRTLLM Kernels (#32564)

2026-03-03 10:39:50 -08:00

fp_quant.py

…

gguf.py

…

gptq_marlin.py

…

gptq.py

…

inc.py

…

input_quant_fp8.py

…

kv_cache.py

…

modelopt.py

Add support for ModelOpt MXFP8 MoE models (#35986)

2026-03-08 13:00:05 -07:00

moe_wna16.py

…

mxfp4.py

[2/N] Elastic EP Milestone 2: Integrating NIXL-EP (#35627)

2026-03-13 09:25:33 -04:00

petit.py

…

ptpc_fp8.py

[Refactor] Remove dead or duplicate func utils or variables (#35318)

2026-02-26 10:57:56 -05:00

qutlass_utils.py

…

schema.py

…

torchao.py

[Bugfix][CI] fix typos (#34934)

2026-03-05 17:05:46 +00:00