Andreas KaratzasandOpenAI Codex 394beb633b [Bugfix][ROCm] Use batch DMA for CPU KV cache loads (#49843) ...

Signed-off-by: Andreas Karatzas <akaratza@amd.com>
Co-authored-by: OpenAI Codex <noreply@openai.com>

2026-07-27 02:18:01 -07:00

..

attention

[Bugfix] Normalize sparse MLA warmup compression ratios (#49392)

2026-07-27 07:02:48 +00:00

core

[3/N][Core][KV Connector] Support reliable partial-tail KV offload for sub-block prompts (#49502)

2026-07-26 23:22:17 -07:00

cudagraph

[CI] Isolate cudagraph tests in child processes (#49510)

2026-07-23 17:16:19 +00:00

determinism

[Bug] Fix batch invariance rms norm comparison (#49603)

2026-07-23 12:27:38 -06:00

distributed

[Core] Add prefill step cadence for better non-PD DP balancing (#44558)

2026-06-16 13:17:18 -07:00

e2e

[Kernel] ReplaySSM: cache SSM inputs for faster Mamba2 standard decode (#48018)

2026-07-24 09:39:49 -07:00

ec_connector

[EC Connector] CPU Offloading EC Connector (#47423)

2026-07-13 20:09:41 +03:00

engine

[Frontend] expose stream_interval as req sampling param (#49754)

2026-07-27 11:30:37 +08:00

executor

[Core][AMD] Propagate shutdown timeout to MultiprocExecutor (#43154)

2026-06-12 15:13:31 -05:00

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

[3/N][Core][KV Connector] Support reliable partial-tail KV offload for sub-block prompts (#49502)

2026-07-26 23:22:17 -07:00

kv_offload

[Bugfix][ROCm] Use batch DMA for CPU KV cache loads (#49843)

2026-07-27 02:18:01 -07:00

logits_processors

[Bugfix] Fix thinking_token_budget not enforced after natural </think> re-entry (#45984)

2026-07-10 22:47:51 +00:00

metrics

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

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

sample

Revert "[Sampler] Stop upcasting logits to fp32 in apply_sampling_params" (#48641) (#49033)

2026-07-21 09:36:45 +01:00

shutdown

[ROCm][CI] Make tests/v1/shutdown an importable package (#47085)

2026-06-29 21:01:27 -05:00

simple_kv_offload

[Core] Add MRV2 virtual-batch PCP for MLA (#46570)

2026-07-19 02:53:15 +00:00

spec_decode

[CI] Explicitly tear down speculative decode runners (#49910)

2026-07-27 05:32:46 +00:00

streaming_input

[CI][Bugfix] Fix and wire streaming-input tests (#49356)

2026-07-22 00:35:23 +00:00

structured_output

[Bugfix][Structured Output][Spec Decode] Advance grammar across reasoning boundary (#44993)

2026-07-23 09:14:15 -07:00

tracing

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

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

worker

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

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

__init__.py

[V1] AsyncLLM Implementation (#9826)

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

test_kv_cache_spec_registry.py

[KVCache] Support Pluggable KVCacheSpec (#37505)

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

test_oracle.py

[Docs] Clean up speculators docs (#34065)

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

test_outputs.py

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

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

test_request.py

[Refactor] Rename WAITING_FOR_FSM to WAITING_FOR_STRUCTURED_OUTPUT_GRAMMAR (#38048)

2026-03-25 11:41:44 -04:00

test_serial_utils.py

Add tensor IPC transfer mechanism for multimodal data (#32104)

2026-03-21 20:10:20 +00:00

test_tensor_ipc_queue.py

[Test] Refactor hard coded device string in test files under compile/quantization/models/model_executor folders (#38901)

2026-04-15 11:02:35 +08:00

utils.py

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

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