Commits · 3de379de064dd2b636404fab34cf08ce5ce81cd2 · OpenDAS / vllm_cscc

31 Jul, 2025 1 commit
- update unused code · 3de379de
  zhuwenwen authored Jul 31, 2025
  
  3de379de
25 Jul, 2025 1 commit
- set VLLM_USE_V1=1 · e4a84fdc
  zhuwenwen authored Jul 25, 2025
  
  e4a84fdc
24 Jul, 2025 2 commits
- [Frontend] Set MAX_AUDIO_CLIP_FILESIZE_MB via env var instead of hardcoding (#21374) · 63d92abb
  deven-labovitch authored Jul 23, 2025
```
Signed-off-by: Deven Labovitch <deven@videa.ai>
```
  63d92abb
- [Core] Freeze gc during cuda graph capture to speed up init (#21146) · f3137cdd
  Michael Goin authored Jul 23, 2025
```
Signed-off-by: Codex <codex@openai.com>
Signed-off-by: mgoin <mgoin64@gmail.com>
```
  f3137cdd
21 Jul, 2025 1 commit
- [CPU] Enable shared-memory based pipeline parallel for CPU backend (#21289) · a15a50fc
  Li, Jiang authored Jul 22, 2025
```
Signed-off-by: jiang1.li <jiang1.li@intel.com>
```
  a15a50fc
19 Jul, 2025 2 commits
- [bugfix] Fix auto thread-binding when world_size > 1 in CPU backend and refactor code (#21032) · e3a0e43d
  Li, Jiang authored Jul 19, 2025
```
Signed-off-by: jiang1.li <jiang1.li@intel.com>
```
  e3a0e43d
- [NVIDIA] Add SM100 Flashinfer MoE blockscale fp8 backend for low latency (#20645) · 6d0734c5
  Kaixi Hou authored Jul 19, 2025
```
Signed-off-by: kaixih <kaixih@nvidia.com>
Signed-off-by: mgoin <mgoin64@gmail.com>
Co-authored-by: mgoin <mgoin64@gmail.com>
```
  6d0734c5
18 Jul, 2025 1 commit

[Core] FlashInfer CUTLASS fused MoE backend (NVFP4) (#20037) · c7d8724e

Shu Wang authored Jul 17, 2025


Signed-off-by: shuw <shuw@nvidia.com>
Signed-off-by: mgoin <mgoin64@gmail.com>
Co-authored-by: mgoin <mgoin64@gmail.com>

c7d8724e

17 Jul, 2025 2 commits
- [V0 deprecation] Remove V0 HPU backend (#21131) · 4de71463
  Woosuk Kwon authored Jul 17, 2025
```
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
```
  4de71463
- set default block_size and pa · b61f7a69
  zhuwenwen authored Jul 17, 2025
  
  b61f7a69
16 Jul, 2025 1 commit
- [Nvidia] Integrate SM100 cudnn prefill API to MLA prefill (#20411) · 30800b01
  Elfie Guo authored Jul 15, 2025
```
Signed-off-by: Elfie Guo <elfieg@nvidia.com>
Co-authored-by: Elfie Guo <eflieg@nvidia.com>
```
  30800b01
15 Jul, 2025 2 commits
- [Bug Fix] get_distributed_init_method should get the ip from get_ip i… (#20889) · 10be2094
  Chen LI authored Jul 15, 2025
```
Signed-off-by: Chen Li <lcpingping@gmail.com>
Co-authored-by: Russell Bryant <rbryant@redhat.com>
Signed-off-by: Russell Bryant <rbryant@redhat.com>
```
  10be2094
- [cold start] replace VLLM_COMPILE_DEPYF with debug_dump_dir (#20940) · 91b3d190
  Boyuan Feng authored Jul 14, 2025
```
Signed-off-by: Boyuan Feng <boyuan@meta.com>
```
  91b3d190
12 Jul, 2025 1 commit
- [cold start time] add envs.VLLM_COMPILE_DEPYF to guard decompile (#20790) · c1c8ca57
  Boyuan Feng authored Jul 11, 2025
```
Signed-off-by: Boyuan Feng <boyuan@meta.com>
```
  c1c8ca57
11 Jul, 2025 1 commit

[Core] Add Flashinfer TRTLLM Backend for Flashinfer decode path (SM100). (#19825) · 7bd4c37a

Pavani Majety authored Jul 11, 2025


Signed-off-by: Pavani Majety <pmajety@nvidia.com>
Signed-off-by: mgoin <mgoin64@gmail.com>
Co-authored-by: shuw <shuw@nvidia.com>
Co-authored-by: mgoin <mgoin64@gmail.com>

7bd4c37a

10 Jul, 2025 2 commits
- [V0][V1][Core] Add outlines integration for V1, and update V0 integration. (#15975) · d6902ce7
  Nathan Hoos authored Jul 10, 2025
```
Signed-off-by: Nathan Hoos <thwackyy.y@gmail.com>
```
  d6902ce7
- add apex rmsnorm · 3e0a595d
  zhuwenwen authored Jul 10, 2025
  
  3e0a595d
09 Jul, 2025 1 commit

[Feature][Quantization] MXFP4 support for MOE models (#17888) · 332d4cb1

fxmarty-amd authored Jul 09, 2025


Signed-off-by: Felix Marty <felmarty@amd.com>
Signed-off-by: Bowen Bao <bowenbao@amd.com>
Signed-off-by: Felix Marty <Felix.Marty@amd.com>
Co-authored-by: Bowen Bao <bowenbao@amd.com>

332d4cb1

08 Jul, 2025 1 commit
- [PD][Nixl] Remote consumer READ timeout for clearing request blocks (#20139) · 71d1d75b
  Nicolò Lucchesi authored Jul 08, 2025
```
Signed-off-by: NickLucche <nlucches@redhat.com>
```
  71d1d75b
03 Jul, 2025 2 commits
- update VLLM_FLASH_ATTN_BACKEND to VLLM_FLASH_ATTN_V1 · 64fc5a29
  zhuwenwen authored Jul 03, 2025
  
  64fc5a29
- update VLLM_USE_FLASH_ATTN_BACKEND to VLLM_USE_FLASH_ATTN_PA · e036115e
  zhuwenwen authored Jul 03, 2025
  
  e036115e
02 Jul, 2025 2 commits
- set VLLM_USE_NN=1 · 058b32ae
  zhuwenwen authored Jul 02, 2025
  
  058b32ae
- [Refactor] Remove Unused Env `VLLM_ENABLE_MOE_ALIGN_BLOCK_SIZE_TRITON` (#20334) · 9dae7d46
  Wentao Ye authored Jul 01, 2025
```
Signed-off-by: yewentao256 <zhyanwentao@126.com>
```
  9dae7d46
01 Jul, 2025 1 commit
- [CPU] Update custom ops for the CPU backend (#20255) · 6cc1e7d9
  Li, Jiang authored Jul 01, 2025
```
Signed-off-by: jiang1.li <jiang1.li@intel.com>
```
  6cc1e7d9
27 Jun, 2025 2 commits
- update cutlass fa and pa · 4ddb5447
  zhuwenwen authored Jun 27, 2025
  
  4ddb5447
- [Feature] add quick all reduce (#19744) · 0740e29b
  li haoyang authored Jun 27, 2025
```
Signed-off-by: ilmarkov <imarkov@redhat.com>
Signed-off-by: Haoyang Li <Haoyang.Li@amd.com>
Co-authored-by: ilmarkov <imarkov@redhat.com>
```
  0740e29b
25 Jun, 2025 3 commits
- [TPU] Add TPU specific var VLLM_TPU_MOST_MODEL_LEN (#19919) · 2d7620c3
  Chenyaaang authored Jun 25, 2025
```
Signed-off-by: Chenyaaang <chenyangli@google.com>
```
  2d7620c3
- [Quantization] Add compressed-tensors emulations support for NVFP4 (#19879) · 02c97d9a
  Dipika Sikka authored Jun 25, 2025
```
Signed-off-by: Dipika Sikka <dipikasikka1@gmail.com>
Signed-off-by: Dipika <dipikasikka1@gmail.com>
```
  02c97d9a
- [Kernels][Bugfix] Use torch op for all kernels in FusedMoE forward. Add... · 015fab8c
  bnellnm authored Jun 25, 2025
```
[Kernels][Bugfix] Use torch op for all kernels in FusedMoE forward.  Add additional testing for cudagraphs. (#19717)
Signed-off-by: Bill Nell <bnell@redhat.com>
```
  015fab8c
23 Jun, 2025 1 commit
- [Misc] Configurable timeout for execute_model RPC calls via env var (#19544) · f39ab2d4
  jinqinn authored Jun 23, 2025
```
Signed-off-by: jinqinn <goodqinjin@163.com>
```
  f39ab2d4
22 Jun, 2025 1 commit
- [BugFix] Add an env to disable moe chunking to work around compile incompatibility (#19642) · 33d51f59
  Ye (Charlotte) Qi authored Jun 22, 2025
```
Signed-off-by: Ye (Charlotte) Qi <yeq@meta.com>
```
  33d51f59
20 Jun, 2025 1 commit
- Export NaNs in logits to scheduler_stats if output is corrupted (#18777) · 2e3e3c86
  Vlad Tiberiu Mihailescu authored Jun 20, 2025
```
Signed-off-by: Vlad Mihailescu <vtmihailescu@gmail.com>
```
  2e3e3c86
18 Jun, 2025 1 commit

[Hardware][AMD] integrate aiter chunked prefill into vllm (#18596) · 8b6e1d63

Zzz9990 authored Jun 18, 2025


Signed-off-by: fsx950223 <fsx950223@outlook.com>
Signed-off-by: charlifu <charlifu@amd.com>
Co-authored-by: fsx950223 <fsx950223@outlook.com>
Co-authored-by: charlifu <charlifu@amd.com>

8b6e1d63

17 Jun, 2025 1 commit
- [V1][Kernel] Flashinfer HND KV cache layout (#19280) · 4c8f64fa
  Nicolò Lucchesi authored Jun 17, 2025
```
Signed-off-by: NickLucche <nlucches@redhat.com>
```
  4c8f64fa
12 Jun, 2025 3 commits
- [Misc] Turn MOE_DP_CHUNK_SIZE into an env var (#19506) · 9d880f59
  Varun Sundar Rabindranath authored Jun 12, 2025
  
  9d880f59
- [torch.compile][ROCm] Fuse quantization onto attention using a torch.compile pass (#16756) · f98548b9
  Luka Govedič authored Jun 12, 2025
```
Signed-off-by: Luka Govedič <lgovedic@redhat.com>
Co-authored-by: Sage Moore <sage@neuralmagic.com>
```
  f98548b9
- add VLLM_TBO_DECODE_BS to support and setting the min bs on tbo decode · aa906d98
  lizhigong authored Jun 12, 2025
  
  aa906d98
10 Jun, 2025 1 commit
- Automatically bind CPU OMP Threads of a rank to CPU ids of a NUMA node. (#17930) · 9368cc90
  Louie Tsai authored Jun 09, 2025
```
Signed-off-by: Tsai, Louie <louie.tsai@intel.com>
Co-authored-by: Li, Jiang <bigpyj64@gmail.com>
```
  9368cc90
09 Jun, 2025 2 commits
- [Frontend] Make TIMEOUT_KEEP_ALIVE configurable through env var (#18472) · 31f58be9
  liusiqian-tal authored Jun 10, 2025
```
Signed-off-by: liusiqian <liusiqian@tal.com>
```
  31f58be9
- [Misc] Fixes and Optimizations for DeepEP + DeepGEMM combination. (#19298) · 5cf2daea
  Varun Sundar Rabindranath authored Jun 09, 2025
```
Signed-off-by: Varun <vsundarr@redhat.com>
Co-authored-by: Varun <vsundarr@redhat.com>
```
  5cf2daea