Commits · a8141fa649d1296488cc5de2b479fed460bb34f4 · OpenDAS / vllm_cscc

30 Oct, 2025 3 commits
- [Refactor] Remove `VLLM_DEEPEP_LOW_LATENCY_ALLOW_NVLINK` (#27750) · a8141fa6
  Wentao Ye authored Oct 30, 2025
```
Signed-off-by: yewentao256 <zhyanwentao@126.com>
```
  a8141fa6
- [Misc] Replace CUDA_VISIBLE_DEVICES in DP with torch.cuda.set_device for... · 60f76baa
  Ilya Markov authored Oct 30, 2025
```
[Misc] Replace CUDA_VISIBLE_DEVICES in DP with torch.cuda.set_device for device selection on cuda-like devices (#27564)
Signed-off-by: ilmarkov <markovilya197@gmail.com>
Co-authored-by: Tyler Michael Smith <tlrmchlsmth@gmail.com>
```
  60f76baa
- [BugFix] Handle unscheduled requests properly when async scheduling (#27756) · 2ce5c5d3
  Nick Hill authored Oct 29, 2025
```
Signed-off-by: Nick Hill <nhill@redhat.com>
```
  2ce5c5d3
29 Oct, 2025 4 commits
- [BugFix] Fix handling of resumed reqs in `SharedStorageConnector` (#27719) · d4aa1443
  Nick Hill authored Oct 29, 2025
```
Signed-off-by: Nick Hill <nhill@redhat.com>
```
  d4aa1443
- [KVConnector] Add metrics to Prometheus-Grafana dashboard (#26811) · accb8fab
  Nicolò Lucchesi authored Oct 29, 2025
```
Signed-off-by: NickLucche <nlucches@redhat.com>
Signed-off-by: Mark McLoughlin <markmc@redhat.com>
Co-authored-by: Mark McLoughlin <markmc@redhat.com>
```
  accb8fab
- [Chore] Optimize P2PNCCLEngine `http_address` (#27488) · 5522fb27
  Wentao Ye authored Oct 29, 2025
```
Signed-off-by: yewentao256 <zhyanwentao@126.com>
```
  5522fb27
- [KV Connector] Update lmcache connector with latest compatibility (#27681) · a4a4f0f6
  Shaoting authored Oct 28, 2025
```
Signed-off-by: Samuel Shen <slshen@uchicago.edu>
Co-authored-by: Samuel Shen <slshen@uchicago.edu>
```
  a4a4f0f6
28 Oct, 2025 2 commits

[Bugfix] Fix allocation & free logic of SingleWriterShmRingBuffer (#27117) · 02af36df

Kero Liang authored Oct 28, 2025


Signed-off-by: Kero Liang <kerorek@outlook.com>
Signed-off-by: Roger Wang <hey@rogerw.io>
Co-authored-by: donglu <donglu@cohere.com>
Co-authored-by: Roger Wang <hey@rogerw.io>

02af36df

[nit]: Fix import for the lmcache integration (#27600) · 05e034f0

Samuel Shen authored Oct 28, 2025


Signed-off-by: Samuel Shen <slshen@uchicago.edu>
Co-authored-by: Samuel Shen <slshen@uchicago.edu>

05e034f0

27 Oct, 2025 1 commit
- [Misc] Clean up utils (#27552) · 7c2bdb83
  Cyrus Leung authored Oct 27, 2025
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  7c2bdb83
25 Oct, 2025 3 commits
- [Core][Hybrid allocator + kv connector 1/n] Enable hybrid allocator + KV cache connector (#25712) · b8535403
  Kuntai Du authored Oct 24, 2025
```
Signed-off-by: KuntaiDu <kuntai@uchicago.edu>
Signed-off-by: Kuntai Du <kuntai@uchicago.edu>
```
  b8535403
- Revert "[Misc] Remove use of CUDA_VISIBLE_DEVICES for device selectio… (#27502) · 56ed7609
  Zhuohan Li authored Oct 24, 2025
  
  56ed7609
- [KVConnector] Migrate the LMCache integration code to be vLLM native (#25542) · 83f478bb
  Yihua Cheng authored Oct 24, 2025
```
Signed-off-by: ApostaC <yihua98@uchicago.edu>
```
  83f478bb
24 Oct, 2025 6 commits
- [Log] Optimize Startup Log (#26740) · 52efc34e
  Wentao Ye authored Oct 24, 2025
```
Signed-off-by: yewentao256 <zhyanwentao@126.com>
```
  52efc34e
- [Distributed] Basic set of configuration for large EP deployment on GB200 (#27328) · d95d0f4b
  Pengchao Wang authored Oct 24, 2025
```
Signed-off-by: Pengchao Wang <wpc@fb.com>
Co-authored-by: Lu Fang <30275821+houseroad@users.noreply.github.com>
```
  d95d0f4b
- [Bugfix] Fix MultiConnector stats reconstruction across process boundaries (#27366) · 7e1d697b
  kourosh hakhamaneshi authored Oct 24, 2025
```
Signed-off-by: Kourosh Hakhamaneshi <Kourosh@anyscale.com>
Co-authored-by: Nicolò Lucchesi <nlucches@redhat.com>
```
  7e1d697b
- [NIXL][BUGFIX] delay done_recving queue cleanup to bottom of get_finished (#27297) · 699d62e6
  Chendi.Xue authored Oct 24, 2025
```
Signed-off-by: Chendi Xue <chendi.xue@intel.com>
```
  699d62e6
- [Misc] Avoid "PyTorch non-writable tensors" warning in RayPPCommunicator (#27443) · 09a6a49e
  Rui Qiao authored Oct 23, 2025
```
Signed-off-by: Rui Qiao <ruisearch42@gmail.com>
```
  09a6a49e
- Fix EventPublisherFactory logic for disabled KV cache events (#27419) · c528b900
  usberkeley authored Oct 24, 2025
```
Signed-off-by: Bradley <bradley.b.pitt@gmail.com>
```
  c528b900
23 Oct, 2025 1 commit

[Misc] Remove use of CUDA_VISIBLE_DEVICES for device selection (fix DP slow... · 237cf6d3

Ilya Markov authored Oct 23, 2025


[Misc] Remove use of CUDA_VISIBLE_DEVICES for device selection (fix DP slow startup time &c) (#26709)
Signed-off-by: ilmarkov <markovilya197@gmail.com>
Co-authored-by: Tyler Michael Smith <tlrmchlsmth@gmail.com>

237cf6d3

22 Oct, 2025 6 commits

[Chore] Separate out system utilities from vllm.utils (#27201) · a0003b56
dongbo910220 authored Oct 23, 2025
```
Signed-off-by: dongbo910220 <1275604947@qq.com>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>
```
a0003b56

[Feature] publisher default set zmq in kv_event config (#26915) · 8669c69a

rongfu.leng authored Oct 23, 2025


Signed-off-by: rongfu.leng <rongfu.leng@daocloud.io>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>

8669c69a

[P/D] Dynamic `kv_output_aggregator` collect size (#26734) · 4dfdb821
Nicolò Lucchesi authored Oct 22, 2025
```
Signed-off-by: NickLucche <nlucches@redhat.com>
```
4dfdb821

[NIXL] use Host buffer to support TP_ratio > 1 for XPU (#27140) · 7c4767f1

Chendi.Xue authored Oct 22, 2025


Signed-off-by: Chendi Xue <chendi.xue@intel.com>
Signed-off-by: Chendi.Xue <chendi.xue@intel.com>
Co-authored-by: Nicolò Lucchesi <nicolo.lucchesi@gmail.com>

7c4767f1

[NIXL] Terminate handshake listener thread in shutdown (#26404) · 4ca13a86
Mark McLoughlin authored Oct 22, 2025
```
Signed-off-by: Mark McLoughlin <markmc@redhat.com>
```
4ca13a86

[Chore] Separate out optional dependency checks from vllm.utils (#27207) · 3ae082c3

dongbo910220 authored Oct 22, 2025

Signed-off-by: dongbo910220 <1275604947@qq.com>
Signed-off-by: dongbo910220 <32610838+dongbo910220@users.noreply.github.com>
Co-authored-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>

3ae082c3

21 Oct, 2025 6 commits
- [P/D] KVConnector for decode benchmarking (#25986) · 6c2eef5a
  Tyler Michael Smith authored Oct 21, 2025
```
Signed-off-by: Tyler Michael Smith <tlrmchlsmth@gmail.com>
Signed-off-by: Tyler Michael Smith <tyler@neuralmagic.com>
```
  6c2eef5a
- [V0 Deprecation] Remove V0 executors (#27142) · 647214f3
  Nick Hill authored Oct 21, 2025
```
Signed-off-by: Nick Hill <nhill@redhat.com>
```
  647214f3
- [Bugfix][P/D] Reduce num_threads used by nixl ucx backend (#27196) · ddeec11b
  David Whyte-Gray authored Oct 21, 2025
```
Signed-off-by: David Whyte-Gray <40244437+dagrayvid@users.noreply.github.com>
```
  ddeec11b
- [Chore] Separate out NCCL utilities from vllm.utils (#27197) · 6c728f77
  dongbo910220 authored Oct 21, 2025
```
Signed-off-by: dongbo910220 <1275604947@qq.com>
```
  6c728f77
- [Nixl] Minor refactor to handshake related metadata (#26410) · 72f431e7
  Nicolò Lucchesi authored Oct 21, 2025
```
Signed-off-by: NickLucche <nlucches@redhat.com>
```
  72f431e7
- create is_in_the_same_node on cpu (#26832) · 0eb8f2b8
  Lunwen He authored Oct 20, 2025
```
Co-authored-by: Lunwen He <lunwenh@meta.com>
```
  0eb8f2b8
19 Oct, 2025 1 commit

[Chore] Separate out `vllm.utils.network_utils` (#27164) · 7a6c8c3f

iAmir97 authored Oct 19, 2025


Signed-off-by: iAmir97 <Amir.balwel@embeddedllm.com>
Co-authored-by: iAmir97 <Amir.balwel@embeddedllm.com>

7a6c8c3f

18 Oct, 2025 3 commits
- [Minor] Add some clarifying comments to recent changes (#27130) · 3b450752
  Nick Hill authored Oct 18, 2025
```
Signed-off-by: Nick Hill <nhill@redhat.com>
```
  3b450752
- Fix incorrect string formatting in barrier timeout exceptions (#27149) · 168e578e
  Yongtao Huang authored Oct 19, 2025
```
Signed-off-by: Yongtao Huang <yongtaoh2022@gmail.com>
```
  168e578e
- [Chore] Clean up pytorch helper functions in `vllm.utils` (#26908) · 6ac5e06f
  Isotr0py authored Oct 19, 2025
```
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
Signed-off-by: isotr0py <2037008807@qq.com>
```
  6ac5e06f
17 Oct, 2025 3 commits
- [Docs] Replace `rst` style double-backtick with `md` single-backtick (#27091) · 6c9fdbf7
  Harry Mellor authored Oct 17, 2025
```
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
  6c9fdbf7
- [Perf] Exploit out-of-band buffers in shm_broadcast (#26961) · ab81379e
  Nick Hill authored Oct 16, 2025
```
Signed-off-by: Nick Hill <nhill@redhat.com>
```
  ab81379e
- [Chore] Separate out `vllm.utils.importlib` (#27022) · 4d4d6bad
  Cyrus Leung authored Oct 17, 2025
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  4d4d6bad
16 Oct, 2025 1 commit
- [small][batch invariance] Rename the env and internal flags to simplify usage (#26855) · b2f78cba
  Bram Wasti authored Oct 16, 2025
```
Signed-off-by: Bram Wasti <bwasti@meta.com>
```
  b2f78cba