Bruno VolpatoandCodex 61f084b5f3 [Bugfix][Multimodal] Fix per-video cache option reuse (#55203) ...

Signed-off-by: bvolpato <brunocvcunha@gmail.com>
Co-authored-by: Codex <noreply@openai.com>

2026-10-11 06:21:55 +00:00

..

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] Keep batch x heads out of gridDim.z in the GLM-5.3-Flash fused recurrent KDA kernel (#56974)

2026-10-05 09:31:45 +00:00

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

[Bugfix][Mooncake] Save the EAGLE attention proof with hybrid Mamba partial tails (#60695)

2026-10-10 00:08:08 +00:00

language

[Bugfix] Treat max_tokens as output upper bound, not input-space reservation (#57035)

2026-10-10 01:15:22 +08:00

multimodal

[Bugfix][Multimodal] Fix per-video cache option reuse (#55203)

2026-10-11 06:21:55 +00:00

quantization

[ROCm][MoE] Support MiMo-V2.6 MXFP4 on gfx942 (#58262)

2026-09-30 17:23:00 +08:00

qwen4_exp

[ROCm][Perf] Fuse main QK-norm/RoPE/gate and KV-cache write into the AMD QSA prepare launch (#59732)

2026-10-09 21:14:49 +08:00

transformers

[CI] Allowlist-shrink batch 2: wire 9 tests/models/ files into Buildkite, fix 2 stale bugs found (#59050)

2026-10-06 21:16:53 -07:00

__init__.py

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

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

registry.py

[Bugfix][Model] K-EXAONE: restore loading of pre-2.0 configs and apply RoPE to the MTP layer (#60187)

2026-10-10 15:05:55 +00:00

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_aiter_mega_moe.py

[ROCm][DSv4] AITER MegaMoEV2 Integration For DeepSeek V4 (#59685)

2026-10-07 09:35:53 -05:00

test_deepseek_v4_dspark_rocm.py

[CI] Fix failing test_deepseek_v4_rocm_dspark* tests (#60462)

2026-10-07 14:18:19 -07:00

test_deepseek_v4_fi_moe_ep.py

[feat] FlashInfer CuteDSL MegaMoE integration (#54049)

2026-10-02 15:43:33 -04:00

test_deepseek_v4_mega_moe.py

[Refactor] Abstract DeepGemm MegaMOE backend (#58053)

2026-10-08 05:05:39 +00:00

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][DSv4] AITER MegaMoEV2 Integration For DeepSeek V4 (#59685)

2026-10-07 09:35:53 -05:00

test_deepseek_v41_decoder_replay_layers.py

[Perf][DSv4.1] Trim the last KV-source layer in decoder replay (#59894)

2026-10-09 06:07:49 +00:00

test_deepseek_v41_replay_batch.py

[Perf][DSv4.1] Trim the last KV-source layer in decoder replay (#59894)

2026-10-09 06:07:49 +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

[Bugfix][Kimi-K3] Declare max_tp_shards on the DSpark MLA KV cache spec (#59733)

2026-10-08 00:33:32 -04:00

test_dsv41_mono_decode.py

[ROCm][Perf][DSv4.1] Mono decode layer for DeepSeek-V4.1-Flash on MI355X (#60397)

2026-10-09 20:53:18 -05:00

test_dsv41_mono_layers.py

[ROCm][Perf][DSv4.1] Mono decode layer for DeepSeek-V4.1-Flash on MI355X (#60397)

2026-10-09 20:53:18 -05:00

test_dsv41_mono_numerics.py

[ROCm][Perf][DSv4.1] Mono decode layer for DeepSeek-V4.1-Flash on MI355X (#60397)

2026-10-09 20:53:18 -05:00

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

[Misc] Remove code paths for Transformers < 5.16.1 (#59762)

2026-10-02 11:17:24 +00:00