Commits · 2216a4e5c5e95be00376562237c2324ea1ff5272 · OpenDAS / vllm_cscc

22 Oct, 2024 1 commit
- [Hardware][CPU] using current_platform.is_cpu (#9536) · 3ddbe255
  wangshuai09 authored Oct 22, 2024
  
  3ddbe255
18 Oct, 2024 1 commit
- 删除v2 8192限制 · a7e3c9d6
  zhangshao authored Oct 18, 2024
  
  a7e3c9d6
17 Oct, 2024 1 commit
- add VLLM_USE_TC_PAGED_ATTN to convert tc pa · f164171b
  zhuwenwen authored Oct 17, 2024
  
  f164171b
16 Oct, 2024 1 commit
- update paged_attn.py · 85e8224c
  zhuwenwen authored Oct 16, 2024
  
  85e8224c
11 Oct, 2024 1 commit
- [Model] support telechat_12B · 6d4b207a
  zhuwenwen authored Oct 11, 2024
  
  6d4b207a
24 Sep, 2024 1 commit
- 优化pa小batch性能（pa_v2），优化pa小seq性能(pa_v1)，reusekv=16优化 · 2b91ac93
  zhuwenwen authored Sep 24, 2024
  
  2b91ac93
20 Sep, 2024 1 commit
- add pa tc · 0c70376b
  zhuwenwen authored Sep 20, 2024
  
  0c70376b
18 Sep, 2024 1 commit
- [CI/Build] Avoid CUDA initialization (#8534) · 6ffa3f31
  Cyrus Leung authored Sep 18, 2024
  
  6ffa3f31
21 Aug, 2024 5 commits
- Update refactoring operation · 668ec4ef
  zhuwenwen authored Aug 21, 2024
  
  668ec4ef
- Refactoring the optimized kernel · 0aa2480f
  zhuwenwen authored Aug 21, 2024
  
  0aa2480f
- update VLLM_USE_OPT_OP to use opt kernels · 8a325c18
  zhuwenwen authored Aug 21, 2024
  
  8a325c18
- Add VLLM_USE_PA_PRINT_PARAM flag to print pa size · 2f9e0bad
  zhuwenwen authored Aug 21, 2024
  
  2f9e0bad
- Add VLLM_USE_PA_PRINT_PARAM flag to print pa size · ef037256
  zhuwenwen authored Aug 21, 2024
  
  ef037256
20 Aug, 2024 1 commit
- Refactoring the optimized kernel · 4405f82c
  zhuwenwen authored Aug 20, 2024
  
  4405f82c
15 Aug, 2024 2 commits
- update triton fa config for head_dim>128 · 3b2b3046
  zhuwenwen authored Aug 15, 2024
  
  3b2b3046
- update triton fa config for head_dim>128 · 8ae929fb
  zhuwenwen authored Aug 15, 2024
  
  8ae929fb
14 Aug, 2024 2 commits
- update the configuration of triton fa · 33290303
  zhuwenwen authored Aug 14, 2024
  
  33290303
- update the configuration of triton fa · 3e2c63a7
  zhuwenwen authored Aug 14, 2024
  
  3e2c63a7
13 Aug, 2024 2 commits
- update prefix_prefill params · e658bf7f
  zhuwenwen authored Aug 13, 2024
  
  e658bf7f
- update prefix_prefill params · f39feef5
  zhuwenwen authored Aug 13, 2024
  
  f39feef5
12 Aug, 2024 1 commit
- [Core/Bugfix] Add FP8 K/V Scale and dtype conversion for prefix/prefill Triton Kernel (#7208) · a046f863
  jon-chuang authored Aug 12, 2024
```
Co-authored-by: Cody Yu <hao.yu.cody@gmail.com>
```
  a046f863
29 Jul, 2024 1 commit
- [Bugfix] Allow vllm to still work if triton is not installed. (#6786) · 9a7e2d05
  Thomas Parnell authored Jul 29, 2024
```
Signed-off-by: Thomas Parnell <tpa@zurich.ibm.com>
```
  9a7e2d05
27 Jul, 2024 1 commit
- [Model] H2O Danube3-4b (#6451) · 14dbd5a7
  Joe authored Jul 26, 2024
  
  14dbd5a7
25 Jul, 2024 2 commits
- update prefix_prefill params · c9305344
  zhuwenwen authored Jul 25, 2024
  
  c9305344
- update prefix_prefill params · d69fb7b2
  zhuwenwen authored Jul 25, 2024
  
  d69fb7b2
16 Jul, 2024 1 commit
- [Kernel][Attention] Separate `Attention.kv_scale` into `k_scale` and `v_scale` (#6081) · 978aed53
  Michael Goin authored Jul 16, 2024
  
  978aed53
15 Jul, 2024 1 commit
- [Bugfix] use float32 precision in samplers/test_logprobs.py for comparing with HF (#6409) · 4ef95b0f
  Thomas Parnell authored Jul 15, 2024
```
Signed-off-by: Thomas Parnell <tpa@zurich.ibm.com>
```
  4ef95b0f
13 Jul, 2024 1 commit
- [Bugfix] Fix hard-coded value of x in context_attention_fwd (#6373) · e1684a76
  Thomas Parnell authored Jul 13, 2024
```
Signed-off-by: Thomas Parnell <tpa@zurich.ibm.com>
```
  e1684a76
12 Jul, 2024 1 commit
- [Model][Phi3-Small] Remove scipy from blocksparse_attention (#6343) · d59eb984
  Michael Goin authored Jul 11, 2024
  
  d59eb984
06 Jul, 2024 1 commit
- Use triton fa by default · 1863c926
  zhuwenwen authored Jul 06, 2024
  
  1863c926
05 Jul, 2024 1 commit
- [Bugfix] Add verbose error if scipy is missing for blocksparse attention (#5695) · e58294dd
  JGSweets authored Jul 05, 2024
  
  e58294dd
03 Jul, 2024 1 commit
- [hardware][misc] introduce platform abstraction (#6080) · 482045ee
  youkaichao authored Jul 02, 2024
  
  482045ee
01 Jul, 2024 1 commit
- [misc][cuda] use nvml to avoid accidentally cuda initialization (#6007) · 614aa512
  youkaichao authored Jun 30, 2024
  
  614aa512
20 Jun, 2024 2 commits
- update triton fa · e2df3544
  zhuwenwen authored Jun 20, 2024
  
  e2df3544
- update triton fa · 83e4e0fe
  zhuwenwen authored Jun 20, 2024
  
  83e4e0fe
13 Jun, 2024 1 commit
- [Hardware][Intel] Optimize CPU backend and add more performance tips (#4971) · 80aa7e91
  Li, Jiang authored Jun 14, 2024
```
Co-authored-by: Jianan Gu <jianan.gu@intel.com>
```
  80aa7e91
31 May, 2024 1 commit
- [Model] Support MAP-NEO model (#5081) · a22dea54
  SnowDist authored May 31, 2024
```
Co-authored-by: Zhuohan Li <zhuohan123@gmail.com>
```
  a22dea54
28 May, 2024 1 commit
- [Core] Sliding window for block manager v2 (#4545) · d4f39859
  Michał Moskal authored May 27, 2024
```
Co-authored-by: Ruth Evans <ruthevans@Ruths-MacBook-Pro.local>
```
  d4f39859
25 May, 2024 1 commit

[Kernel][Backend][Model] Blocksparse flash attention kernel and Phi-3-Small model (#4799) · 8e192ff9

Eric Xihui Lin authored May 25, 2024


Co-authored-by: beagleski <yunanzhang@microsoft.com>
Co-authored-by: bapatra <bapatra@microsoft.com>
Co-authored-by: Barun Patra <codedecde@users.noreply.github.com>
Co-authored-by: Michael Goin <michael@neuralmagic.com>

8e192ff9

16 May, 2024 1 commit
- [ROCm][AMD][Bugfix] adding a missing triton autotune config (#4845) · b5853f99
  Hongxia Yang authored May 16, 2024
  
  b5853f99