5 people 2617fe9383 [Bugfix][GLM-5.3-Flash] kpool corruption with speculative decoding (#58454) ...

Signed-off-by: Matt Mastracci <matthew@mastracci.com>
Signed-off-by: Robert Shaw <114415538+robertgshaw2-redhat@users.noreply.github.com>
Co-authored-by: Yifan Qiao <yifanqiao@inferact.ai>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
Co-authored-by: Robert Shaw <114415538+robertgshaw2-redhat@users.noreply.github.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>

2026-09-25 12:51:34 -04:00

..

attention

[Perf][DSv4] Fuse inverse RoPE + FP8 quant into FlashInfer sparse MLA (#58621)

2026-09-24 23:26:50 -07:00

core

[Bugfix][Quantization] Fix MXFP8 startup crash on layers below mm_mxfp8 shape limits (#54223)

2026-09-25 02:54:11 +00:00

helion

[Refactor] Move auxiliary files out of the repository root (#58572)

2026-09-24 12:38:56 -07:00

ir

[CI] Ignore ruff D209, rejoin the docstrings it split, and silence incompatible-rule warnings (#57212)

2026-09-16 10:57:24 -07:00

mamba

[Feature] Triton kernel dispatcher (#43048)

2026-09-25 04:07:43 +00:00

moe

[MoE] Defer the TRTLLM-Gen top-k finalize on the modular path (#58635)

2026-09-25 15:38:29 +08:00

quantization

[Perf][Kernel] Vectorized flat abs-max for dynamic per-tensor FP8 quantization (#58194)

2026-09-25 09:19:48 -06:00

scripts

[CI/Build][ROCm] Run the TileLang HIP symbol checks in their own interpreter (#53117)

2026-08-21 16:17:42 -05:00

turboquant

[Kernel][ROCm][Perf] FlyDSL decode-attention kernel for 4-bit TurboQuant KV cache (#47896)

2026-08-11 08:45:39 -07:00

__init__.py

[CI/Build] Move test_utils.py to tests/utils.py (#4425)

2024-05-13 23:50:09 +09:00

allclose_default.py

Convert formatting to use ruff instead of yapf + isort (#26247)

2025-10-05 07:06:22 -07:00

conftest.py

[CI] Fix stale/fragile untethered kernels-root tests (#49423)

2026-07-22 14:43:07 -06:00

quant_utils.py

[ROCm] Fix CI runtime and tests for MI355 DPX (#58244)

2026-09-24 23:15:11 -05:00

test_apply_repetition_penalties.py

Add pydocstyle to the ruff rules (#52136)

2026-09-16 16:44:29 +00:00

test_awq_int4_to_int8.py

Add pydocstyle to the ruff rules (#52136)

2026-09-16 16:44:29 +00:00

test_bf16_skinny_gemm.py

[Bugfix][Kimi-K3] Fix KDA projection overlap on Hopper (#55426)

2026-09-11 19:07:30 +00:00

test_bf16x3_router_gemm_cutedsl.py

[Perf] Improve BF16x3 router GEMM accuracy and make it default on sm100 (#55899)

2026-09-09 07:33:12 -07:00

test_cache_kernels.py

Add pydocstyle to the ruff rules (#52136)

2026-09-16 16:44:29 +00:00

test_compressor_kv_cache.py

[Perf][DSV4.1] Optimize MegaMoE staging and NVFP4 cache gathers (#57604)

2026-09-18 12:57:19 -07:00

test_concat_mla_q.py

[Bugfix][ROCm] Use the platform FP8 range in the concat MLA q test (#58153)

2026-09-22 18:05:33 -05:00

test_cp_gather_fp8.py

[CI] Ignore ruff D209, rejoin the docstrings it split, and silence incompatible-rule warnings (#57212)

2026-09-16 10:57:24 -07:00

test_deepseek_v4_cpu_kernels.py

[CI] Ignore ruff D209, rejoin the docstrings it split, and silence incompatible-rule warnings (#57212)

2026-09-16 10:57:24 -07:00

test_dsv41_mega_attn_layouts.py

[Model][DSv4.1] FlashMLA mega attention and the NVFP4 compressed KV cache (#56935)

2026-09-16 03:07:50 -07:00

test_engram.py

[Perf][Engram] Serialize offloaded lookups and pack host tables into huge pages (#56926)

2026-09-25 10:52:02 +08:00

test_fla_layernorm_guard.py

[ROCm][Perf] Avoid extra reshape kernel in Qwen GDN output norm (#47842)

2026-09-22 14:38:16 +08:00

test_flashinfer_bf16_gemm.py

[kernel] Integrate FlashInfer BF16 CuTeDSL Low Latency GEMM (#50572)

2026-08-27 22:29:12 +00:00

test_flex_attention.py

Add pydocstyle to the ruff rules (#52136)

2026-09-16 16:44:29 +00:00

test_fp32_router_gemm.py

[CI] Ignore ruff D209, rejoin the docstrings it split, and silence incompatible-rule warnings (#57212)

2026-09-16 10:57:24 -07:00

test_fused_deepseek_v4_qnorm_rope_kv_insert.py

[CI][ROCm] Add ten AMD parity groups (#57876)

2026-09-21 11:08:06 +00:00

test_fused_deepseek_v32_norm_rope.py

[ROCm][Model][Bugfix] Enable GLM-5.2-MXFP4 on the deepseek_v32 path and fix sparse attention correctness (#51915)

2026-09-22 18:08:51 -05:00

test_fused_gdn_post_conv.py

[Model] Support Qwen3.8-Flash-Next (#53896)

2026-08-31 05:57:56 +00:00

test_fused_indexer_q_rope_quant.py

[CI] Ignore ruff D209, rejoin the docstrings it split, and silence incompatible-rule warnings (#57212)

2026-09-16 10:57:24 -07:00

test_fused_inv_rope_fp8_quant.py

[CI] Ignore ruff D209, rejoin the docstrings it split, and silence incompatible-rule warnings (#57212)

2026-09-16 10:57:24 -07:00

test_fused_minimax_m3_qknorm_rope_kv_insert.py

[Attention][MiniMax-M3] Add MSA speculative decode verification (#50032)

2026-08-02 13:46:55 -07:00

test_fused_qk_norm_rope_gate.py

[Kernel][Perf] Enable fused QK-norm + partial MRoPE + gate for Qwen3.6 (#52676)

2026-08-24 18:28:49 -07:00

test_fused_quant_activation.py

[Perf][Kernel][Quantization] Fuse ReLU2 with static FP8 activation quantization (#53793)

2026-09-14 10:26:15 -07:00

test_fused_recurrent_packed_decode.py

[Bugfix][Kernel] Keep packed GDN decode beta in FP32 (#53877)

2026-08-30 22:15:36 +08:00

test_fused_sigmoid_gating_delta_rule.py

[CI] Fix stale/fragile untethered kernels-root tests (#49423)

2026-07-22 14:43:07 -06:00

test_gate_linear_rocm_dispatch.py

[ROCm][Perf] Add low-M FP32 router GEMM for gfx950 (#54845)

2026-09-03 10:42:25 -07:00

test_gemm_rs_ar.py

[Kernel][DSV4.1] Fuse MXFP8 wo_b GEMM with sequence-parallel reduce-scatter (#57428)

2026-09-22 01:07:17 -07:00

test_kpool_decode_update_batched.py

[Bugfix][GLM-5.3-Flash] kpool corruption with speculative decoding (#58454)

2026-09-25 12:51:34 -04:00

test_ll_bf16_gemm.py

[Kimi-K3][Perf] Prefetch ll_bf16 router weights for M=1 (#53524)

2026-09-01 21:40:19 +00:00

test_mhc_jit_warmup.py

[Perf][DSv4.1] Fold the mHC post block into the delayed pre projection (#56633)

2026-09-14 18:57:37 +00:00

test_mhc_kernels.py

[Bugfix][DSV4.1] Restrict mHC overlap to full CUDA graphs (#57874)

2026-09-21 01:16:59 -07:00

test_mhc_tilelang_jit.py

[Bugfix][ROCm][GLM-5.3-Flash] Apply deferred tilelang.jit already on attribute access (#57192)

2026-09-17 12:02:39 +00:00

test_minimax_m3_amd_ops.py

[Bugfix][Quantization] Fix MXFP8 startup crash on layers below mm_mxfp8 shape limits (#54223)

2026-09-25 02:54:11 +00:00

test_minimax_m3_sparse_attn_fp8_scale.py

[ROCm][MiniMax-M3] Add AITER sparse paged attention (#47287)

2026-07-12 19:27:29 -07:00

test_onednn.py

[CPU] Speedup LM Head on Arm CPUs (#55352)

2026-09-11 16:21:14 +08:00

test_relu2_fp8_quant.py

[Perf][Kernel][Quantization] Fuse ReLU2 with static FP8 activation quantization (#53793)

2026-09-14 10:26:15 -07:00

test_rocm_fp32_router_gemm.py

[ROCm][Perf] Add low-M FP32 router GEMM for gfx950 (#54845)

2026-09-03 10:42:25 -07:00

test_shuffle_rows.py

[CI] Ignore ruff D209, rejoin the docstrings it split, and silence incompatible-rule warnings (#57212)

2026-09-16 10:57:24 -07:00

test_top_k_per_row.py

[GLM-5.3-Flash] Route kpool indexer top-k through the shared SparseIndexerTopk dispatcher (#57546)

2026-09-20 11:17:59 +00:00

utils.py

Add pydocstyle to the ruff rules (#52136)

2026-09-16 16:44:29 +00:00