MINJUN GILandOr Ozeri f12fe10c5c [Bugfix][KV Offload] Track cache recency once per request (#51787) ...

Signed-off-by: mindungil <alswnsrlf12@naver.com>
Co-authored-by: Or Ozeri <oro@il.ibm.com>

2026-09-16 10:47:26 +03:00

..

attention

[Refactor][GLM-5.3-Flash] Move sparse_attn_indexer_kpool into the model folder and split AMD/NVIDIA (#55358)

2026-09-16 05:50:35 +00:00

core

[Bugfix] Fix incorrect Mamba block allocation estimate that prevents request admission (#57050)

2026-09-16 07:23:20 +00:00

cudagraph

[CI] Initialize ubatch runner in cudagraph unit test (#56808)

2026-09-14 13:37:08 -05:00

determinism

[Test][Determinism] Cover VLM batch invariance in default execution mode (#56528)

2026-09-13 10:22:03 -04:00

distributed

[CI][ROCm] Raise AMD job and server readiness timeouts (#55308)

2026-09-05 10:50:51 +08:00

e2e

[Cleanup] Remove vestigial tpu_input_batch.py (#56898)

2026-09-14 21:29:15 -07:00

ec_connector

[Bugfix][EPD] Preserve media processing options in encoder requests (#56786)

2026-09-14 10:05:13 +00:00

engine

[Frontend] Share max_num_queued_reqs across API server processes (#54746)

2026-09-15 14:50:26 +00:00

executor

[Bugfix] Release worker RPC payload before next dequeue (#51979)

2026-08-24 07:27:36 -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_connector

[Bugfix][KV Offload] Track cache recency once per request (#51787)

2026-09-16 10:47:26 +03:00

kv_offload

[Bugfix][KV Offload] Track cache recency once per request (#51787)

2026-09-16 10:47:26 +03:00

logits_processors

[Structured Output] Let terminal grammars stop under min_tokens (II) (#54218)

2026-08-31 20:39:27 +04:00

metrics

[V1][Metrics] Support Sliding Window Attention (SWA) and hybrid layers in MFU/MBU estimation (#55624)

2026-09-14 16:04:55 +00:00

sample

[6/N][warmup][DSv4] Migrate sampling, and DFlash JIT kernels (#56323)

2026-09-12 17:24:24 -07:00

shutdown

[6/N][warmup][DSv4] Migrate sampling, and DFlash JIT kernels (#56323)

2026-09-12 17:24:24 -07:00

simple_kv_offload

[Bugfix][KV Offload] Submit CPU stores on no-forward steps (#56621)

2026-09-13 05:56:14 +00:00

spec_decode

[Refactor] StructuredOutputManager x Speculative Decoding Refactor (#48200)

2026-09-15 09:48:49 -04:00

streaming_input

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

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

structured_output

[Refactor] StructuredOutputManager x Speculative Decoding Refactor (#48200)

2026-09-15 09:48:49 -04:00

tracing

[CI] Fix segfault in tracing test (#47299)

2026-07-01 14:00:37 +00:00

worker

[Kernel] Use Murmur3 RNG for Gumbel sampling (#51367)

2026-09-15 23:52:26 -07:00

__init__.py

[V1] AsyncLLM Implementation (#9826)

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

test_kv_cache_spec_registry.py

[3/N] HiSparse: host-resident sparse-MLA decode hot-buffering (#53781)

2026-09-12 00:36:47 -04:00

test_oracle.py

[Docs] Clean up speculators docs (#34065)

2026-02-18 13:48:11 -08:00

test_outputs.py

[CI][XPU] skip test_sampling_mask_tensors_match_finite_support on XPU (#55852)

2026-09-09 11:16:03 +08:00

test_request.py

feat(frontend): session id plumbing into requests (#48048)

2026-08-03 22:18:58 +00:00

test_serial_utils.py

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

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

test_tensor_ipc_queue.py

[CI] Stabilize tensor IPC multiprocessing tests (#50804)

2026-08-12 10:16:43 +08:00

utils.py

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

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