Commits · 98b4d389ed27f09fd185ade889a02f640a3ff0b4 · OpenDAS / vllm_cscc

15 Nov, 2025 4 commits

Cyrus Leung authored Nov 15, 2025


Signed-off-by: Jialin Ouyang <Jialin.Ouyang@gmail.com>
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
Co-authored-by: Jialin Ouyang <Jialin.Ouyang@gmail.com>

98b4d389

[NIXL] heterogeneous block_size support (#26759) · c9e66585

Chendi.Xue authored Nov 14, 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>

c9e66585

Revert "[Core] Performance: Use list[np.ndarray] instead of list[list… (#28773) · ac86bff8
Nick Hill authored Nov 14, 2025

ac86bff8

[Core] Performance: Use list[np.ndarray] instead of list[list[int]] for output... · 186352b2

Jialin Ouyang authored Nov 14, 2025


[Core] Performance: Use list[np.ndarray] instead of list[list[int]] for output tokens for GC optimization (#26368)
Signed-off-by: Jialin Ouyang <Jialin.Ouyang@gmail.com>

186352b2

13 Nov, 2025 1 commit
- [KV Connector] Test async mode in scheduler tests (#28550) · 6e25b1cd
  Mark McLoughlin authored Nov 13, 2025
```
Signed-off-by: Mark McLoughlin <markmc@redhat.com>
```
  6e25b1cd
11 Nov, 2025 1 commit
- [NIXL] Generalize block-first backend layouts (FlashInfer-like) (#28282) · a7ef3eb0
  Nicolò Lucchesi authored Nov 11, 2025
  
  a7ef3eb0
09 Nov, 2025 1 commit
- [Core] Simplify async KV output aggregation (#28327) · 289eb6c5
  Nick Hill authored Nov 09, 2025
```
Signed-off-by: Nick Hill <nhill@redhat.com>
```
  289eb6c5
07 Nov, 2025 2 commits
- [PerfFix] Avoid separate thread for MP executor shm spin (take 2) (#28319) · 67a2da89
  Nick Hill authored Nov 07, 2025
```
Signed-off-by: Nick Hill <nhill@redhat.com>
```
  67a2da89
- Revert "[PerfFix] Avoid separate thread for MP executor shm spin (#28012)" (#28289) · 68a72a5c
  Nicolò Lucchesi authored Nov 07, 2025
```
Signed-off-by: NickLucche <nlucches@redhat.com>
```
  68a72a5c
05 Nov, 2025 2 commits

[CI]: Add LMCacheConnector Unit Tests (#27852) · 40db1944

Samuel Shen authored Nov 05, 2025


Signed-off-by: Samuel Shen <slshen@uchciago.edu>
Co-authored-by: Samuel Shen <slshen@uchciago.edu>
Co-authored-by: Yihua Cheng <yihua98@uchicago.edu>

40db1944

[Hybrid allocator + kv connector] revert connector test changes related to... · 86dca07d

Kuntai Du authored Nov 05, 2025


[Hybrid allocator + kv connector] revert connector test changes related to hybrid allocator (#28011)
Signed-off-by: KuntaiDu <kuntai@uchicago.edu>

86dca07d

04 Nov, 2025 2 commits
- [PerfFix] Avoid separate thread for MP executor shm spin (#28012) · c9f66da8
  Nick Hill authored Nov 04, 2025
```
Signed-off-by: Nick Hill <nhill@redhat.com>
```
  c9f66da8
- [KV Connector] Make KVCacheConfig an explicit constructor argument (#27887) · 58279c60
  Mark McLoughlin authored Nov 04, 2025
```
Signed-off-by: Mark McLoughlin <markmc@redhat.com>
```
  58279c60
01 Nov, 2025 2 commits

[Add] cmdline argument parsing for KV cache offloading modules (#27621) · e6751188

Yihua Cheng authored Nov 01, 2025

Signed-off-by: ApostaC <yihua98@uchicago.edu>
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>

e6751188

[Core] Async scheduling + structured outputs compatibility (#26866) · 0cdbe7b7
Nick Hill authored Oct 31, 2025
```
Signed-off-by: Nick Hill <nhill@redhat.com>
```
0cdbe7b7

31 Oct, 2025 1 commit

[Bugfix] Missing NIXL metadata for handshake initialization if instance spans multi-node (#26338) · d6517be3

GuanLuo authored Nov 01, 2025


Signed-off-by: Guan Luo <gluo@nvidia.com>
Signed-off-by: GuanLuo <41310872+GuanLuo@users.noreply.github.com>
Signed-off-by: Guan Luo <41310872+GuanLuo@users.noreply.github.com>
Co-authored-by: Nicolò Lucchesi <nlucches@redhat.com>

d6517be3

25 Oct, 2025 1 commit
- [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
24 Oct, 2025 1 commit
- [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
22 Oct, 2025 2 commits
- [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] Terminate handshake listener thread in shutdown (#26404) · 4ca13a86
  Mark McLoughlin authored Oct 22, 2025
```
Signed-off-by: Mark McLoughlin <markmc@redhat.com>
```
  4ca13a86
21 Oct, 2025 2 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
- [Nixl] Minor refactor to handshake related metadata (#26410) · 72f431e7
  Nicolò Lucchesi authored Oct 21, 2025
```
Signed-off-by: NickLucche <nlucches@redhat.com>
```
  72f431e7
19 Oct, 2025 1 commit
- [Chore] Separate out hashing utilities from vllm.utils (#27151) · 8a297115
  dongbo910220 authored Oct 19, 2025
```
Signed-off-by: dongbo910220 <1275604947@qq.com>
```
  8a297115
14 Oct, 2025 3 commits
- [Core] Streamline some structured output related code (#26737) · 4aed506b
  Nick Hill authored Oct 14, 2025
```
Signed-off-by: Nick Hill <nhill@redhat.com>
```
  4aed506b
- [KVConnector][Metrics] Aggregate scheduler-side KVConnectorStats (#26046) · 720394de
  Qier Li authored Oct 14, 2025
```
Signed-off-by: Qier Li <kevin44036@gmail.com>
```
  720394de
- [NIXL][HeteroTP] Enable KV transfer from HND prefill to NHD decode (#26556) · 7e6edb14
  Chendi.Xue authored Oct 14, 2025
```
Signed-off-by: Chendi Xue <chendi.xue@intel.com>
```
  7e6edb14
13 Oct, 2025 1 commit
- [P/D] [NixlConnector] kv load recovery integration (#26171) · 53c9a7ce
  Will Eaton authored Oct 13, 2025
```
Signed-off-by: Will Eaton <weaton@redhat.com>
```
  53c9a7ce
12 Oct, 2025 1 commit
- Update `Optional[x]` -> `x | None` and `Union[x, y]` to `x | y` (#26633) · 8fcaaf6a
  Harry Mellor authored Oct 12, 2025
```
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
  8fcaaf6a
10 Oct, 2025 2 commits
- [NIXL] Ignore abort on already-finished request (#25067) · 784c2311
  Mark McLoughlin authored Oct 10, 2025
```
Signed-off-by: Mark McLoughlin <markmc@redhat.com>
```
  784c2311
- [bugfix][DCP] fix block_size of hash in DCP prefix caching (#26296) · 606b00e8
  Chen Zhang authored Oct 10, 2025
```
Signed-off-by: Chen Zhang <zhangch99@outlook.com>
```
  606b00e8
06 Oct, 2025 1 commit
- Fix per file ruff ignores related to line length (#26262) · 6c046382
  Harry Mellor authored Oct 06, 2025
```
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
  6c046382
05 Oct, 2025 1 commit
- Convert formatting to use `ruff` instead of `yapf` + `isort` (#26247) · d6953beb
  Harry Mellor authored Oct 05, 2025
```
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
  d6953beb
04 Oct, 2025 1 commit
- [Bugfix] Fix `_reqs_to_process` leak on abort (#26012) · 2a6dc67e
  Nicolò Lucchesi authored Oct 04, 2025
```
Signed-off-by: NickLucche <nlucches@redhat.com>
```
  2a6dc67e
03 Oct, 2025 1 commit
- [NIXL][Misc] Expose metrics from NIXL for logging to CLI (#25388) · 48f30902
  Nicolò Lucchesi authored Oct 03, 2025
```
Signed-off-by: NickLucche <nlucches@redhat.com>
```
  48f30902
30 Sep, 2025 3 commits

[V1] [P/D] Add Support for KV Load Failure Recovery (#19330) · 9a9f48df
David Ben-David authored Oct 01, 2025
```
Signed-off-by: David Ben-David <davidb@pliops.com>
Co-authored-by: David Ben-David <davidb@pliops.com>
```
9a9f48df

[CI] Move applicable tests to CPU (#24080) · bc546f76

Reza Barazesh authored Sep 30, 2025


Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>

bc546f76

[NIXL] Add support for MLA caches with different latent dim (#25902) · 80608ba5

Nicolò Lucchesi authored Sep 30, 2025


Signed-off-by: NickLucche <nlucches@redhat.com>
Signed-off-by: Chen Zhang <zhangch99@outlook.com>
Co-authored-by: Chen Zhang <zhangch99@outlook.com>

80608ba5

26 Sep, 2025 1 commit
- [CI] Fix test_shared_storage_connector_hashes (#25748) · 2827b3f4
  Chauncey authored Sep 26, 2025
```
Signed-off-by: chaunceyjiang <chaunceyjiang@gmail.com>
```
  2827b3f4
23 Sep, 2025 2 commits
- [P/D] Support NIXL connector to disconnect during a clean shutdown (#24423) · f05a4f0e
  Chauncey authored Sep 23, 2025
```
Signed-off-by: chaunceyjiang <chaunceyjiang@gmail.com>
Co-authored-by: Mark McLoughlin <markmc@redhat.com>
```
  f05a4f0e
- [NIXL][OOT platform] support nixl_connector with oot platform and other nixl_backend (#25121) · 5774b0a1
  Chendi.Xue authored Sep 22, 2025
```
Signed-off-by: Chendi Xue <Chendi.Xue@intel.com>
```
  5774b0a1