Commits · fb6af8bc086328ca6659e72d11ffd4309ce4de22 · OpenDAS / vllm_cscc

14 Jul, 2024 1 commit
- [ Misc ] Apply MoE Refactor to Deepseekv2 To Support Fp8 (#6417) · fb6af8bc
  Robert Shaw authored Jul 13, 2024
  
  fb6af8bc
13 Jul, 2024 1 commit
- [ Misc ] More Cleanup of Marlin (#6359) · babf52da
  Robert Shaw authored Jul 13, 2024
```
Co-authored-by: Robert Shaw <rshaw@neuralmagic.com>
```
  babf52da
12 Jul, 2024 4 commits
- [Bugfix] Fix illegal memory access in FP8 MoE kernel (#6382) · 75f64d8b
  Cody Yu authored Jul 12, 2024
  
  75f64d8b
- [Bugfix] Fix dtype mismatch in PaliGemma (#6367) · 024ad87c
  Cyrus Leung authored Jul 12, 2024
  
  024ad87c
- [ Misc ] Support Models With Bias in `compressed-tensors` integration (#6356) · aea19f09
  Robert Shaw authored Jul 12, 2024
  
  aea19f09
- [ Misc ] Remove separate bias add (#6353) · 6047187c
  Robert Shaw authored Jul 12, 2024
  
  6047187c
11 Jul, 2024 4 commits
- [bug fix] Fix llava next feature size calculation. (#6339) · 1df43de9
  xwjiang2010 authored Jul 11, 2024
```
Signed-off-by: Xiaowei Jiang <xwjiang2010@gmail.com>
```
  1df43de9
- [ Misc ] Refactor Marlin Python Utilities (#6082) · b675069d
  Robert Shaw authored Jul 11, 2024
```
Co-authored-by: Robert Shaw <rshaw@neuralmagic.com>
```
  b675069d
- [Bugfix] GPTBigCodeForCausalLM: Remove lm_head from supported_lora_modules. (#6326) · 8a1415cf
  Thomas Parnell authored Jul 11, 2024
```
Signed-off-by: Thomas Parnell <tpa@zurich.ibm.com>
Co-authored-by: Travis Johnson <tsjohnso@us.ibm.com>
```
  8a1415cf
- [Doc] Remove comments incorrectly copied from another project (#6286) · 99ded1e1
  daquexian authored Jul 11, 2024
  
  99ded1e1
10 Jul, 2024 3 commits
- [Bugfix] MLPSpeculator: Use ParallelLMHead in tie_weights=False case. (#6303) · c38eba30
  Thomas Parnell authored Jul 10, 2024
```
Signed-off-by: Thomas Parnell <tpa@zurich.ibm.com>
```
  c38eba30
- [Bugfix] Support 2D input shape in MoE layer (#6287) · e72ae80b
  Woosuk Kwon authored Jul 10, 2024
  
  e72ae80b
- [Speculative Decoding] Medusa Implementation with Top-1 proposer (#4978) · 2416b26e
  Abhinav Goyal authored Jul 10, 2024
  
  2416b26e
09 Jul, 2024 1 commit
- [Bugfix]fix and needs_scalar_to_array logic check (#6238) · d3a24513
  Baoyuan Qi authored Jul 10, 2024
```
Co-authored-by: Robert Shaw <114415538+robertgshaw2-neuralmagic@users.noreply.github.com>
```
  d3a24513
08 Jul, 2024 3 commits
- [Bugfix] Mamba cache Cuda Graph padding (#6214) · ddc369fb
  tomeras91 authored Jul 08, 2024
  
  ddc369fb
- [Bugfix] use diskcache in outlines _get_guide #5436 (#6203) · 185ad31f
  Eric authored Jul 09, 2024
  
  185ad31f
- [Kernel] reloading fused_moe config on the last chunk (#6210) · f7a8fa39
  Avshalom Manevich authored Jul 08, 2024
  
  f7a8fa39
07 Jul, 2024 2 commits
- [ Misc ] Support Fp8 via `llm-compressor` (#6110) · abfe705a
  Robert Shaw authored Jul 07, 2024
```
Co-authored-by: Robert Shaw <rshaw@neuralmagic>
```
  abfe705a
- [Model] Add PaliGemma (#5189) · 6206dcb2
  Roger Wang authored Jul 06, 2024
```
Co-authored-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
```
  6206dcb2
05 Jul, 2024 2 commits
- [VLM] Cleanup validation and update docs (#6149) · ea4b5704
  Cyrus Leung authored Jul 05, 2024
  
  ea4b5704
- [VLM] Improve consistency between feature size calculation and dummy data for profiling (#6146) · a41357e9
  Roger Wang authored Jul 04, 2024
  
  a41357e9
04 Jul, 2024 2 commits
- [VLM] Calculate maximum number of multi-modal tokens by model (#6121) · ae96ef8f
  Cyrus Leung authored Jul 05, 2024
  
  ae96ef8f
- [Kernel][Model] logits_soft_cap for Gemma2 with flashinfer (#6051) · 69ec3ca1
  Lily Liu authored Jul 04, 2024
```
Co-authored-by: Simon Mo <simon.mo@hey.com>
```
  69ec3ca1
03 Jul, 2024 6 commits
- [ Misc ] Clean Up `CompressedTensorsW8A8` (#6113) · 62963d12
  Robert Shaw authored Jul 03, 2024
  
  62963d12
- [vlm] Remove vision language config. (#6089) · d9e98f42
  xwjiang2010 authored Jul 03, 2024
```
Signed-off-by: Xiaowei Jiang <xwjiang2010@gmail.com>
Co-authored-by: Roger Wang <ywang@roblox.com>
```
  d9e98f42
- [Kernel] Expand FP8 support to Ampere GPUs using FP8 Marlin (#5975) · 47f0954a
  Michael Goin authored Jul 03, 2024
  
  47f0954a
- [Bugfix] Fix `compute_logits` in Jamba (#6093) · 7cd2ebb0
  Roger Wang authored Jul 03, 2024
  
  7cd2ebb0
- [Core] Dynamic image size support for VLMs (#5276) · 9831aec4
  Cyrus Leung authored Jul 03, 2024
```
Signed-off-by: Xiaowei Jiang <xwjiang2010@gmail.com>
Co-authored-by: Xiaowei Jiang <xwjiang2010@gmail.com>
Co-authored-by: ywang96 <ywang@roblox.com>
Co-authored-by: xwjiang2010 <87673679+xwjiang2010@users.noreply.github.com>
Co-authored-by: Roger Wang <136131678+ywang96@users.noreply.github.com>
```
  9831aec4
- [hardware][misc] introduce platform abstraction (#6080) · 482045ee
  youkaichao authored Jul 02, 2024
  
  482045ee
02 Jul, 2024 6 commits

[Model] Jamba support (#4115) · 9d6a8daa

Mor Zusman authored Jul 03, 2024


Signed-off-by: Muralidhar Andoorveedu <muralidhar.andoorveedu@centml.ai>
Co-authored-by: Erez Schwartz <erezs@ai21.com>
Co-authored-by: Mor Zusman <morz@ai21.com>
Co-authored-by: tomeras91 <57313761+tomeras91@users.noreply.github.com>
Co-authored-by: Tomer Asida <tomera@ai21.com>
Co-authored-by: Zhuohan Li <zhuohan123@gmail.com>
Co-authored-by: Muralidhar Andoorveedu <muralidhar.andoorveedu@centml.ai>

9d6a8daa

[CORE] Quantized lm-head Framework (#4442) · ee93f4f9
Qubitium-ModelCloud authored Jul 03, 2024
```
Co-authored-by: Robert Shaw <rshaw@neuralmagic.com>
Co-authored-by: ZX <zx@lbx.dev>
```
ee93f4f9

[ Misc ] Refactor MoE to isolate Fp8 From Mixtral (#5970) · 7c008c51

Robert Shaw authored Jul 02, 2024


Co-authored-by: Robert Shaw <rshaw@neuralmagic>
Co-authored-by: Michael Goin <michael@neuralmagic.com>

7c008c51

[Core] Pipeline Parallel Support (#4412) · c5832d2a
Murali Andoorveedu authored Jul 02, 2024
```
Signed-off-by: Muralidhar Andoorveedu <muralidhar.andoorveedu@centml.ai>
```
c5832d2a

[VLM] Remove `image_input_type` from VLM config (#5852) · 98d6682c

xwjiang2010 authored Jul 02, 2024


Signed-off-by: Xiaowei Jiang <xwjiang2010@gmail.com>
Co-authored-by: Cyrus Leung <cyrus.tl.leung@gmail.com>
Co-authored-by: Roger Wang <ywang@roblox.com>

98d6682c

[Core] Optimize block_manager_v2 vs block_manager_v1 (to make V2 default) (#5602) · 3476ed08
Alexander Matveev authored Jul 01, 2024

3476ed08

01 Jul, 2024 4 commits
- [Model] Changes to MLPSpeculator to support tie_weights and input_scale (#5965) · 54600709
  Thomas Parnell authored Jul 02, 2024
```
Signed-off-by: Thomas Parnell <tpa@zurich.ibm.com>
Co-authored-by: Joshua Rosenkranz <jmrosenk@us.ibm.com>
```
  54600709
- [Bugfix] adding chunking mechanism to fused_moe to handle large inputs (#6029) · 12a59959
  Avshalom Manevich authored Jul 02, 2024
  
  12a59959
- [Speculative Decoding 2/2 ] Integrate typical acceptance sampler into Spec Decode Worker (#5348) · 80ca1e6a
  sroy745 authored Jul 01, 2024
  
  80ca1e6a
- [misc][cuda] use nvml to avoid accidentally cuda initialization (#6007) · 614aa512
  youkaichao authored Jun 30, 2024
  
  614aa512
30 Jun, 2024 1 commit
- [ Misc ] Refactor w8a8 to use `process_weights_after_load` (Simplify Weight Loading) (#5940) · af9ad46f
  Robert Shaw authored Jun 30, 2024
```
Co-authored-by: Robert Shaw <rshaw@neuralmagic>
```
  af9ad46f