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

..

attention

[Attention] Use FA4 for MLA prefill (#34732)

2026-03-12 12:10:17 -04:00

fla

[Perf] add packed recurrent fast path for decode (#36596)

2026-03-12 04:01:57 -07:00

fused_moe

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

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

mamba

replace with torch.cuda.device with with torch.accelerator.device_index (#36144)

2026-03-11 23:12:57 -07:00

pooler

fix bugs when token_classify & classify run concurrently (#36614)

2026-03-10 20:16:34 -07:00

quantization

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

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

rotary_embedding

[Hardware] Replace torch.cuda.device_count/current_device/set_device API (#36145)

2026-03-12 07:57:47 -07:00

__init__.py

…

activation.py

…

attention_layer_base.py

…

batch_invariant.py

[Platform] Add current_platform.num_compute_units interface (#35042)

2026-02-24 22:22:49 -08:00

conv.py

…

kda.py

…

layernorm.py

[Hardware] Replace torch.cuda.device_count/current_device/set_device API (#36145)

2026-03-12 07:57:47 -07:00

lightning_attn.py

…

linear.py

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

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

logits_processor.py

[Spec Decode] Reduce TP communication for speculative decoding draft token generation (#34049)

2026-02-22 14:59:16 -08:00

mla.py

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

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

resampler.py

…

sparse_attn_indexer.py

Add XPU MLA Sparse backend for DeepSeek v3.2 (#33230)

2026-03-11 19:19:15 +08:00

utils.py

Improvements to wvSplitKrc skinny GEMM solution (#34304)

2026-03-10 09:14:27 -07:00

vocab_parallel_embedding.py

…