8000 History for docs - ggozad/vllm · GitHub

Repository navigation

Commits

History for

Commits on Oct 27, 2026
- [Docs][KV Connector] Document standalone Mooncake EGM deployment (#63064)
  
  authored
  a5b257a
- [Core][Frontend] Process checkpoint lifecycle with HTTP prepare/status/resume (#62570)
  
  galletas1712
  and
  vllm-agent
  authored
  05a303f
Commits on Oct 26, 2026
- [Bugfix] Initialize valid ModelOpt NVFP4 MoE dummy scales (#63698)
  
  authored
  4f140a2
- [RL] Declare weight ownership and layout on ParamMeta (#63256)
  
  hao-aaron
  and
  claude
  authored
  50a184f
- [Model] Add native support for Lfm2BidirectionalModel (#62201)
  
  Potabk
  and
  wangli
  authored
  0abec73
- [Bugfix][KV Offload] Preserve running request prefixes across LRU store batches (#61050)
  
  authored
  e113018
- [docs] correct NIXL hybrid SSM heterogeneous TP support (#63036)
  
  hlin99
  and
  NickLucche
  authored
  74340c7
- [Metrics][KV Offload] Fill vllm:kv_offload_config_info with the CPU cache capacity (#53902)
  
  amirfr3
  and
  claude
  authored
  5b06b5f
- [docker] add vllm-openai-efa target (#58768)
  
  authored
  ffcabb8
- [KV Offload] Load small CPU-tier hits synchronously within the step (#61961)
  
  kfirtoledo
  and
  orozery
  authored
  fe5fe8b
- [Doc] Kolibri 1 reasoning and tool-call parsing via HF response template (#62885)
  
  wsascha
  and
  claude
  authored
  256d8b4
- [Doc] Update Muse Spark Open (#63651)
  jeejeelee
  authored
  4b1c04e
- [ROCm] Octave KV (`ROCM_OCTAVE`): native 3-bit KV cache backend for AMD GPUs (#59774)
  
  JartX
  and
  tjtanaa
  authored
  00b6c4c
- [Frontend] Add --reasoning-effort-map to rewrite request reasoning efforts (#61094)
  
  robertgshaw2-redhat
  and
  claude
  authored
  41d9d1e
- [Benchmark] Include speculative drafting in bench forward (#63622)
  
  WoosukKwon
  and
  codex
  authored
  39e6a1a
Commits on Oct 25, 2026
- [Benchmark] Add steady-state PP support to bench forward (#63616)
  
  WoosukKwon
  and
  codex
  authored
  a7407ab
- [Benchmark] Add PCP support to vllm bench forward (#63613)
  
  WoosukKwon
  and
  codex
  authored
  237d2ff
- [CI][Benchmarks] Fix attention smoke test backend names and failure exit status (#63177)
  
  johncalesp
  and
  arpera
  authored
  fa2881e
- [Bugfix] Release cached cuBLAS workspaces after daemon warmup (#63451)
  
  tryryry
  and
  vllm-agent
  authored
  b346636
- [Fast Start] Add daemon-to-daemon warmup cache seeding for Preload (#63088)
  
  authored
  94a29d3
- [Model] Add Dory support (#60149)
  
  shan18
  and
  ywang96
  authored
  75fc05a
- [Bugfix][KV Offload] Reject misaligned chunked-local CPU suffix hits (#63266)
  
  authored
  65bc698
Commits on Oct 24, 2026
Commits on Oct 23, 2026
Commits on Oct 22, 2026
- [KV Connector][Mooncake] Expose transfer stats via Prometheus (#56939)
  
  authored
  01ab876
- [Frontend] Expose --sleep-mode-backend on the CLI (#63138)
  Mramaran
  authored
  d0eb5d2

0