Alec e10787894d fix: add periodic vLLM engine stats logging and fix log routing (#6566) ... Signed-off-by: alec-flowers <aflowers@nvidia.com> Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>		2026-02-25 23:45:34 +00:00
..
async-openai	fix(api): preserve interleaved reasoning order for KV cache correctness (#6442)	2026-02-24 02:20:54 +00:00
bench	docs: add multiturn_bench README with speculative prefill demo (#6502)	2026-02-23 15:52:07 -08:00
bindings	fix: add periodic vLLM engine stats logging and fix log routing (#6566)	2026-02-25 23:45:34 +00:00
config	chore: update all copyright headers in repo to 2026 (#5130)	2026-01-02 22:08:23 +00:00
gpu_memory_service	feat: refactor GMS client memory manager with tiered API (#6549)	2026-02-25 23:24:17 +00:00
kv-router	docs: alphabetize backends (SGLang, TensorRT-LLM, vLLM) (#6537)	2026-02-25 10:07:59 -06:00
kvbm-kernels	feat: add kvbm-kernels crate and upgrade cudarc to 0.19 (#6309)	2026-02-23 16:15:28 +00:00
kvbm-logical	chore: cargo machete - remove unused dependencies (#6453)	2026-02-20 19:11:52 +00:00
llm	feat: Tiktoken support (#6460)	2026-02-25 12:46:47 -08:00
memory	fix: gate dynamo-memory numa module behind cfg(target_os = linux) (#6354)	2026-02-18 09:02:00 -08:00
mocker	feat(mocker): add KV cache transfer latency for disagg serving (#6504)	2026-02-24 23:53:28 -08:00
parsers	feat: Kimi K2/K2.5 tool and reasoning parsers (#6407)	2026-02-25 18:19:14 +00:00
runtime	feat: throughput-metrics-source for SLA planner + GlobalPlanner disagg scaling (#6500)	2026-02-25 22:58:24 +00:00
tokens	chore: make core kv-router its own crate (#5677)	2026-01-28 10:42:53 +00:00