3 people 29332cf936 [4/N] Expose HiSparse cache metrics via KV connector stats (#56061) ...

Signed-off-by: NickLucche <nicolo.lucchesi@mistral.ai>
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
Co-authored-by: Lucas Wilkinson <lwilkins@redhat.com>
Co-authored-by: OpenAI Codex <codex@openai.com>

2026-09-12 10:47:55 -07:00

..

attention

[Perf] Fuse DSV4.1 input metadata preparation with Triton (#56562)

2026-09-12 07:20:04 -07:00

core

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

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

engine

[Elastic EP] Reuse CUDA graphs across reconfiguration (#54985)

2026-09-12 10:26:39 -04:00

executor

[Refactor] Remove utils dead code (#53941)

2026-09-08 11:22:09 -04:00

fault_tolerance

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

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

hisparse

[4/N] Expose HiSparse cache metrics via KV connector stats (#56061)

2026-09-12 10:47:55 -07:00

kv_offload

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

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

metrics

[Metrics] Consolidate Prometheus histogram bucket defaults into a single module (#48866)

2026-09-11 10:12:36 -04:00

pool

[Pooling] Improve BGE-M3 sync pooling throughput by up to 3.13% (#53464)

2026-08-24 08:33:32 -04:00

sample

[Core] Triton kernel for small-batch top-p only masking (#54651)

2026-09-03 07:52:47 -07:00

simple_kv_offload

[Bugfix][KV Connector] Only enforce disk block alignment for O_DIRECT (#55424)

2026-09-11 13:12:59 -07:00

spec_decode

[Deprecation] Deprecate items scheduled for 0.29 (#55353)

2026-09-11 08:17:02 -07:00

structured_output

[Bugfix] Avoid MistralCommonBackend for HF tokenizers (#54192)

2026-09-10 17:57:44 +00:00

watermarking

[feature] Watermarked generation and detection (Gumbel-max algorithm) (#54053)

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

worker

[Elastic EP] Reuse CUDA graphs across reconfiguration (#54985)

2026-09-12 10:26:39 -04:00

__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

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

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

kv_cache_layout.py

[6/N][KV-Cache Layout Refactor] Standardize KV cache layout (#51718)

2026-08-21 17:47:49 -07:00

kv_cache_spec_registry.py

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

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

outputs.py

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

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

request.py

[Frontend][Core][Spec Decode] Per-request acceptance stats in OpenAI API responses (#48915)

2026-08-20 15:42:49 -07:00

serial_utils.py

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

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

utils.py

[Bugfix][Frontend] Keep credentials out of the Rust frontend launch log (#53738)

2026-08-25 16:32:12 +00:00