yangzhuxinyzx 74ea7cf330 [Kernel] Add source-sized IQ2_S gated-pair reader ...

Signed-off-by: yangzhuxinyzx <153831768+yangzhuxinyzx@users.noreply.github.com>

2026-10-05 17:52:28 +08:00

..

attention

…

core

…

helion

…

ir

…

mamba

…

moe

…

ple

[Kernel] Decode ordered GGUF PLE packets without identity gather

2026-10-05 15:31:58 +08:00

quantization

[Kernel] Add source-sized IQ2_S gated-pair reader

2026-10-05 17:52:28 +08:00

__init__.py

…

allclose_default.py

…

quant_utils.py

…

test_apply_repetition_penalties.py

…

test_awq_int4_to_int8.py

…

test_cache_kernels.py

…

test_compressor_kv_cache.py

…

test_concat_mla_q.py

…

test_cp_gather_fp8.py

…

test_deepseek_v4_sm70_fp8_software.py

…

test_deepseek_v4_sm70_indexer.py

…

test_deepseek_v4_sm70_qnorm_rope_kv_insert.py

…

test_fla_layernorm_guard.py

…

test_flex_attention.py

…

test_fused_deepseek_v4_qnorm_rope_kv_insert.py

…

test_fused_gdn_post_conv.py

…

test_fused_indexer_q_rope_quant.py

…

test_fused_inv_rope_fp8_quant.py

…

test_fused_quant_activation.py

…

test_fused_recurrent_packed_decode.py

…

test_fused_sigmoid_gating_delta_rule.py

…

test_kda.py

…

test_kpool_decode_update_batched.py

…

test_mhc_fp16_range.py

…

test_mhc_kernels.py

…

test_mhc_sm70_fp16.py

…

test_onednn.py

…

test_ple_disk_rows.py

[Kernel] Prefetch and gather disk-mapped PLE rows on CPU (#885)

2026-10-05 12:18:47 +08:00

test_shuffle_rows.py

…

test_sm70_awq_chunked_w2.py

…

test_sm70_awq_qpn_m1.py

…

test_sm70_deepseek_v4_fp16_gemv.py

…

test_sm70_dflash2_packed_gdn_fp32.py

…

test_sm70_fp16_gemv_silu.py

…

test_sm70_fp16_grouped_verify.py

…

test_sm70_fused_fp16_aux.py

…

test_sm70_gdn_default_projection_tails.py

…

test_sm70_gdn_mixed_spec_verify.py

…

test_sm70_gdn_projection_tails.py

…

test_sm70_hc_batch_reuse_contract.py

…

test_sm70_hc_local_batch.py

…

test_sm70_mtp_gdn_direct_output.py

…

test_sm70_mtp_gdn_mixed_qkv.py

…

test_sm70_mtp_ple_conv.py

…

test_sm70_mtp_router_batch.py

…

test_sm70_mtp_shared_batch.py

…

test_sm70_mtp_strided_qkv.py

…

test_sm70_ple_ngram_batch.py

…

test_sm70_qpn_concurrency.py

…

test_sm70_qsa_page4_plan.py

…

test_sm70_qwen35_gdn_split.py

…

test_sm70_rmsnorm_gated_exact.py

…

test_sm70_shared_gate_epilogue.py

…

test_sm70_small_moe_routing.py

…

test_top_k_per_row.py

…

utils.py

…