Nick HillandWill Eaton d1d61f3351 [BugFix] Make DP work with connector-delayed new requests (#18559) ...

Signed-off-by: Nick Hill <nhill@redhat.com>
Co-authored-by: Will Eaton <weaton@redhat.com>

2025-05-29 18:04:18 +00:00

..

core

[v1] Redo "Support multiple KV cache groups in GPU model runner (#17945)" (#18593)

2025-05-23 09:39:47 -07:00

e2e

[V1][Spec Decode] Make eagle compatible with prefix caching. (#17137)

2025-04-27 09:29:43 -07:00

engine

[BugFix] Make DP work with connector-delayed new requests (#18559)

2025-05-29 18:04:18 +00:00

entrypoints

[Bugfix] Migrate to REGEX Library to prevent catastrophic backtracking (#18454)

2025-05-23 16:16:26 -07:00

kv_connector

[Bugfix][Nixl] Fix Preemption Bug (#18631)

2025-05-23 23:30:16 +00:00

metrics

[Misc] Add Ray Prometheus logger to V1 (#17925)

2025-05-16 01:02:42 -07:00

sample

[Bugfix] Migrate to REGEX Library to prevent catastrophic backtracking (#18454)

2025-05-23 16:16:26 -07:00

shutdown

[V1][Frontend] Improve Shutdown And Logs (#11737)

2025-04-16 19:48:34 -07:00

spec_decode

[V1][Spec Decode] Support multi-layer eagle draft model (#18030)

2025-05-24 09:45:34 +00:00

structured_output

[Feature][V1] Support tool_choice: required when using Xgrammar as the StructuredOutputBackend. (#17845)

2025-05-12 23:01:31 -07:00

tpu

[TPU] Fix the test_sampler (#17820)

2025-05-08 05:51:33 -04:00

worker

[V1] Allocate kv_cache with stride order for V1 (#18775)

2025-05-29 17:54:16 +00:00

__init__.py

[V1] AsyncLLM Implementation (#9826)

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

test_async_llm_dp.py

[V1][DP] More robust DP/EP dummy request coordination (#16277)

2025-04-22 19:12:15 -07:00

test_metrics_reader.py

[V1][Metrics] Add API for accessing in-memory Prometheus metrics (#17010)

2025-05-27 09:37:06 +00:00

test_oracle.py

[CI/Build] Update bamba test model location (#18544)

2025-05-22 06:01:07 -07:00

test_serial_utils.py

[V1] Add VLLM_ALLOW_INSECURE_SERIALIZATION env var (#17490)

2025-05-08 13:34:02 +08:00

test_utils.py

Update deprecated Python 3.8 typing (#13971)

2025-03-02 17:34:51 -08:00