Siddhant BhartiandClaude Fable 5 0b6aa3c47c [Bugfix][Spec Decode] Size DFlash query buffers for cudagraph-padded batches (#50065) ...

Signed-off-by: siddhant-bharti <sbharti@together.ai>
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>

2026-07-28 19:34:22 +00:00

..

attention

[ROCm][Bugfix] Sanitize AITER paged-MQA logits before sparse top-k for DeepSeek-V4 (#49714)

2026-07-28 11:08:50 -07:00

core

[Core] Fix internal LB load-balancing (#49204)

2026-07-27 14:00:46 +00:00

engine

[Bugfix] Don't reuse engine core payload buffer while zmq is sending it (#50053)

2026-07-28 16:09:28 +00:00

executor

[Elastic EP] Async preparation (#47288)

2026-07-28 05:19:13 -07:00

fault_tolerance

[Feature] Add fault tolerance framework (simplified) for DP+EP external LB deployments (#44428)

2026-07-25 11:49:09 -04:00

kv_offload

[Bugfix][KV Offload][P2P] Scope serve state to fetch rounds (#49877)

2026-07-28 18:01:55 +03:00

metrics

[Front-end] [Messages] Populate num_cache_creation_tokens (#48535)

2026-07-18 13:04:35 -04:00

pool

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

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

sample

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

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

simple_kv_offload

[Bugfix][KV Offload] Propagate EAGLE mode to SimpleCPU coordinator (#49071)

2026-07-20 06:39:11 +00:00

spec_decode

[Bugfix][Spec Decode] Size DFlash query buffers for cudagraph-padded batches (#50065)

2026-07-28 19:34:22 +00:00

structured_output

[Bugfix] Restore structured output logger initialization (#49626)

2026-07-23 11:26:03 -07:00

worker

[Core] Warm up runner-owned Triton kernels before the first request (#49903)

2026-07-28 07:58:02 -07:00

__init__.py

[V1] AsyncLLM Implementation (#9826)

2024-11-11 23:05:38 +00:00

cudagraph_dispatcher.py

[Model] Add DiffusionGemma Support (#45163)

2026-06-11 22:17:35 -07:00

kv_cache_interface.py

[Bugfix] Detect mixed precision in packed KV cache specs (#49623)

2026-07-23 20:07:06 -07:00

kv_cache_spec_registry.py

[KVCache] Support Pluggable KVCacheSpec (#37505)

2026-06-03 09:05:16 -07:00

outputs.py

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

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

request.py

[Core] Preserve Marconi caching with selective hybrid cache retention (#47782)

2026-07-13 21:24:20 +01:00

serial_utils.py

[Core] Ensure memory is pinned prior to async h2d copy (#45424)

2026-06-20 20:02:24 -07:00

utils.py

[Refactor] Move iteration logging to the frontend (#46647)

2026-07-15 17:59:05 -07:00