xaguilar-amdandmergify[bot] <37929162+mergify[bot]@users.noreply.github.com> a7ff44355c [ROCm][Perf] Kimi-K3 Enable sharded latent MoE up-projection under EP (#54956) ...

Signed-off-by: Xavier Aguilar <xavier.aguilarfruto@amd.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>

2026-09-28 10:31:29 -04:00

..

deepseek_v32

[Perf] Optimize DeepSeek V3.2 sequence parallelism (#51434)

2026-08-07 16:51:01 -07:00

fixtures

[BUGFIX] Fix Pixtral consolidated format vision weight loading (#39916)

2026-04-19 22:25:03 -07:00

glm5next

[Bugfix][GLM-5.3-Flash] Run the dense MLP layers on the sequence-parallel shard (#58061)

2026-09-22 21:58:21 +08:00

inkling

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

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

kimi_k3

[ROCm][Perf] Kimi-K3 Enable sharded latent MoE up-projection under EP (#54956)

2026-09-28 10:31:29 -04:00

language

[Spec Decode] Enable Gemma4 DSpark adaptive verification with FlashInfer (#57263)

2026-09-26 17:01:17 +08:00

multimodal

[Bugfix] Fix the two multimodal root tests that fail on main (OpenPangu-VL embed merge, MiMo sink test fixture) (#58900)

2026-09-28 04:52:51 +00:00

quantization

[CI] Share BF16 baselines across quantization comparison tests (#58469)

2026-09-23 19:26:09 -05:00

qwen4_exp

[Perf][Qwen3.8] Reduce PLE metadata construction overhead (#58114)

2026-09-28 20:46:22 +08:00

transformers

[transformer] RMSNorm matching for alternative rsqrt (#54461)

2026-09-24 16:33:06 +00:00

__init__.py

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

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

registry.py

[SpecDecode] Add LiLiCorr drafter (#57934)

2026-09-25 10:08:28 -04:00

test_adapters.py

[Chore] Use Transformers v5 names and drop redundant processor use_fast (#58550)

2026-09-24 14:14:10 +00:00

test_deepseek_v4_dspark_rocm.py

[ROCm][DSv4] Enable DSpark adaptive verification (#52362)

2026-09-21 10:03:41 -05:00

test_deepseek_v4_fi_moe_ep.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_mega_moe.py

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

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

test_deepseek_v4_rocm_compressor_gemm_fusion.py

[ROCm][DSV4][Perf] Fuse DeepSeek V4 C4 compressor GEMMs (#53838)

2026-08-26 23:36:14 +08:00

test_deepseek_v4_rocm_wo_a.py

[ROCm][DSV4][Perf] Use FP8 WO_A output projection (#54894)

2026-09-20 09:13:55 +00:00

test_deepseek_v4_vl_rocm.py

[ROCm][CI] Test AMD DeepSeek V4 MoE routing against a PyTorch reference (#58740)

2026-09-25 18:05:54 +00:00

test_deepseek_v41_replay_start.py

[Feat][Model] Support encoder-side SWA-bounded replay for DeepSeek-V4.1-Flash (#56227)

2026-09-18 15:01:24 -07:00

test_dspark_mla.py

[Perf][DSpark] Stack DeepSeek V4 context WKV projections (#54674)

2026-09-17 00:04:53 -07:00

test_hyv4_rocm.py

[Perf][ROCm] Add a ROCm path for Hy4 and compile the backbone (#57526)

2026-09-21 08:20:43 +00:00

test_initialization.py

[CI] Reclaim GPU memory between model initialization tests (#57362)

2026-09-18 17:04:14 -07:00

test_language_model_cache_is_weak.py

[Bugfix][MRV2] Release model and KV cache on in-process engine shutdown (#54162)

2026-08-28 22:09:08 -07:00

test_qwen3_5_mtp_config.py

[Chore] Use Transformers v5 names and drop redundant processor use_fast (#58550)

2026-09-24 14:14:10 +00:00

test_registry.py

[CI] Only isolate the registry tests that need a fresh process (#58764)

2026-09-26 14:03:45 +08:00

test_terratorch.py

[CI/Build] Skip Prithvi/Terratorch model-registry tests when terratorch is missing (#41389)

2026-04-30 12:47:55 -07:00

test_utils.py

[Model][Gemma4] Load Weights with AutoWeightsLoader (#55911)

2026-09-18 12:07:30 +00:00

test_vision.py

[MM] Add Triton kernel for mm_input_normal. (#56798)

2026-09-25 04:31:20 +00:00

utils.py

[Chore] Use Transformers v5 names and drop redundant processor use_fast (#58550)

2026-09-24 14:14:10 +00:00