Cheng RuiandRui Rui4 Cheng 6664d397bf [Performance][MRV2] Cache logits-processing request state (#52329) ...

Signed-off-by: Rui Rui4 Cheng <chengrui4@lenovo.com>
Co-authored-by: Rui Rui4 Cheng <chengrui4@lenovo.com>

2026-08-17 02:36:41 +00:00

..

__init__.py

[V1] Adding min tokens/repetition/presence/frequence penalties to V1 sampler (#10681)

2024-12-26 19:02:58 +09:00

test_attn_utils.py

[Bugfix][ROCm] Give KV-first attention blocks their own page in hybrid models (#51837)

2026-08-11 16:52:30 -04:00

test_cp_utils.py

DCP supports hybrid attention (#40996)

2026-07-09 21:34:45 -07:00

test_dsv4_packed_zeroer_geometry.py

[5/N][KV-Cache Layout Refactor] Backend-published KV packing via customize_spec (#51704)

2026-08-14 09:47:55 -04:00

test_encoder_runner.py

[Bugfix][MRV2] Support encoder timing stats in model runner V2 (#50020)

2026-08-12 00:00:49 +08:00

test_gpu_autoregressive_speculator.py

[CI][Bugfix][V1] Remove stale FlashAttention metadata arguments (#51854)

2026-08-11 18:54:56 +00:00

test_gpu_bad_words.py

[Bugfix][Model Runner V2][Spec Decode] Fix off-by-one in bad_words draft-prefix matching (#52311)

2026-08-16 09:02:20 +00:00

test_gpu_batch_ordering.py

[Spec Decode] DSpark confidence-scheduled verification (#47808)

2026-08-12 12:27:48 -07:00

test_gpu_block_table.py

[BugFix] Stop dummy runs from writing mamba state through stale block-table rows (#49757)

2026-07-29 01:09:41 +00:00

test_gpu_gumbel_sample.py

[Model Runner V2] Cache draft logits in model's LM head dtype (#50910)

2026-08-05 19:12:46 -07:00

test_gpu_input_batch_v2.py

[XPU][CI] Use platform device in InputBatch V2 test (#49939)

2026-07-27 15:28:02 +08:00

test_gpu_input_batch.py

DCP supports hybrid attention (#40996)

2026-07-09 21:34:45 -07:00

test_gpu_model_runner_mm_gather.py

Encoder cache extension hooks (#48218)

2026-07-24 02:52:00 -07:00

test_gpu_model_runner_v2_eplb.py

[EC Connector] Added Build Connector Worker Meta for EC Connector (#49585)

2026-08-15 15:40:38 -07:00

test_gpu_model_runner.py

[ROCm][AMD] Enable preshuffled sparse indexing for 16-token blocks (#51216)

2026-08-14 12:38:14 -05:00

test_gpu_profiler.py

[Profiler] Add minimal Triton Proton profiling backend (#48789)

2026-08-11 14:51:57 -07:00

test_gpu_rejection_sampler_chunking.py

[MRV2][Spec Decode] Avoid rejection sampler OOM by chunking (#48630)

2026-07-23 18:13:13 +08:00

test_gpu_rejection_sampler_i64.py

[Bugfix][Model Runner V2][Spec Decode] Fix int32 offset overflow in block verification kernels (#47383)

2026-07-02 07:32:38 -07:00

test_gpu_sampler_flags.py

[Performance][MRV2] Cache logits-processing request state (#52329)

2026-08-17 02:36:41 +00:00

test_gpu_thinking_budget.py

[Performance][MRV2] Cache logits-processing request state (#52329)

2026-08-17 02:36:41 +00:00

test_gpu_warmup_blocks.py

[Bugfix][MRV2] Reserve spec-decode lookahead blocks in V2 warmup (#51438)

2026-08-08 23:58:43 +00:00

test_gpu_worker_weight_transfer.py

[Bugfix] Fix level-2 sleep/wake/reload with enable_lora=True (#39935)

2026-08-06 09:13:10 +08:00

test_gpu_worker.py

[Misc] Move PyNvVideoCodec stuff out of gpu worker (#49322)

2026-07-22 10:11:56 +08:00

test_kv_block_zeroer.py

[Bugfix] Bound KV block zeroing launch geometry (#52058)

2026-08-13 03:42:26 +00:00

test_late_interaction_runner.py

[Core] Move MRV1 late_interaction_runner.py out of MRV2 subtree (#48014)

2026-07-08 18:30:11 +00:00

test_mamba_hybrid_model_state.py

[ModelRunnerV2] Fix scalar Mamba state update with int32 mappings (#50327)

2026-08-03 22:05:12 +00:00

test_mamba_utils.py

[Hybrid] Stage the postprocess inputs with a single loop over the request list (#48120)

2026-08-03 20:24:22 +00:00

test_mixed_warmup_gate.py

[BugFix] Gate MRV2 mixed sparse-MLA warmup on max_num_seqs > 1 (#47050)

2026-06-30 16:31:27 +01:00

test_mrope_prompt_embeds.py

[Security] Fix DoS via prompt_embeds on M-RoPE models (#45252)

2026-06-13 10:17:38 +00:00

test_sleep_mode_backend.py

[Core] Make sleep-mode backend capability flags communicator-agnostic (#47243)

2026-07-01 07:17:44 +00:00

test_utils.py

[V0 Deprecation] Refactor kv cache from list to element (#37487)

2026-03-23 20:10:11 -07:00

test_worker_memory_snapshot.py

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

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

test_workspace.py

[Bugfix] Make DSV4 sparse MLA work end-to-end for plain decode, MTP, and DSpark (#51538)

2026-08-15 07:01:32 -07:00

test_xpu_model_runner.py

[XPU] Fix CUDA API shims breaking Torch Dynamo during AOT compile (#43092)

2026-07-06 08:29:20 +08:00