Luka Govedič
7937009a7e
[Kernel] Replaced blockReduce[...] functions with cub::BlockReduce ( #7233 )
...
Co-authored-by: Michael Goin <michael@neuralmagic.com>
2024-08-21 20:18:00 -04:00
Lucas Wilkinson
5288c06aa0
[Kernel] (1/N) Machete - Hopper Optimized Mixed Precision Linear Kernel ( #7174 )
2024-08-20 07:09:33 -06:00
Mor Zusman
7fc23be81c
[Kernel] W8A16 Int8 inside FusedMoE ( #7415 )
2024-08-16 10:06:51 -07:00
Lucas Wilkinson
a8d604ca2a
[Misc] Disambiguate quantized types via a new ScalarType ( #6396 )
2024-08-02 13:51:58 -07:00
Alexander Matveev
75acdaa4b6
[Kernel] Increase precision of GPTQ/AWQ Marlin kernel ( #6795 )
2024-07-27 17:52:33 -04:00
Joe
14dbd5a767
[Model] H2O Danube3-4b ( #6451 )
2024-07-26 20:47:50 -07:00
Michael Goin
978aed5300
[Kernel][Attention] Separate Attention.kv_scale into k_scale and v_scale ( #6081 )
2024-07-16 15:31:32 -07:00
Robert Shaw
b675069d74
[ Misc ] Refactor Marlin Python Utilities ( #6082 )
...
Co-authored-by: Robert Shaw <rshaw@neuralmagic.com>
2024-07-11 15:40:11 +00:00
Michael Goin
8065a7e220
[Frontend] Add FlexibleArgumentParser to support both underscore and dash in names ( #5718 )
2024-06-20 17:00:13 -06:00
Cyrus Leung
0e9164b40a
[mypy] Enable type checking for test directory ( #5017 )
2024-06-15 04:45:31 +00:00
Allen.Dou
d74674bbd9
[Misc] Fix arg names ( #5524 )
2024-06-14 09:47:44 -07:00
Philipp Moritz
51a08e7d8f
[Kernel] Re-tune Mixtral MoE configurations for FP8 on H100 ( #5238 )
2024-06-05 10:59:14 -07:00
Woosuk Kwon
27208be66e
[Kernel] Add back batch size 1536 and 3072 to MoE tuning ( #5242 )
2024-06-04 09:58:47 -07:00
Woosuk Kwon
3a434b07ed
[Kernel] Enhance MoE benchmarking & tuning script ( #4921 )
2024-06-03 20:06:59 -07:00
Cody Yu
e9899fb7a4
[Model] Enable FP8 QKV in MoE and refine kernel tuning script ( #5039 )
2024-05-31 14:29:19 -07:00
SnowDist
a22dea54d3
[Model] Support MAP-NEO model ( #5081 )
...
Co-authored-by: Zhuohan Li <zhuohan123@gmail.com>
2024-05-30 19:24:41 -07:00
Alexander Matveev
6066253296
Marlin 24 prefill performance improvement (about 25% better on average) ( #4983 )
2024-05-23 02:39:27 -04:00
Cody Yu
a3a73ab069
[Misc] Load FP8 kv-cache scaling factors from checkpoints ( #4893 )
...
The 2nd PR for #4532 .
This PR supports loading FP8 kv-cache scaling factors from a FP8 checkpoint (with .kv_scale parameter).
2024-05-22 13:28:20 -07:00
alexm-nm
5c342570d7
Add marlin unit tests and marlin benchmark script ( #4815 )
2024-05-16 09:36:49 -04:00
SangBin Cho
3521ba4f25
[Core][Model runner refactoring 1/N] Refactor attn metadata term ( #4518 )
2024-05-03 10:20:12 -07:00
Philipp Moritz
24bb4fe432
[Kernel] Update fused_moe tuning script for FP8 ( #4457 )
...
This PR updates the tuning script for the fused_moe kernel to support FP8 and also adds configurations for TP4. Note that for the configuration I removed num_warps and num_stages for small batch sizes since that improved performance and brought the benchmarks on par with the numbers before in that regime to make sure this is a strict improvement over the status quo.
All the numbers below are for mistralai/Mixtral-8x7B-Instruct-v0.1, 1000 input and 50 output tokens.
Before this PR (with static activation scaling):
qps = 1: 9.8 ms ITL, 0.49s e2e latency
qps = 2: 9.7 ms ITL, 0.49s e2e latency
qps = 4: 10.1 ms ITL, 0.52s e2e latency
qps = 6: 11.9 ms ITL, 0.59s e2e latency
qps = 8: 14.0 ms ITL, 0.70s e2e latency
qps = 10: 15.7 ms ITL, 0.79s e2e latency
After this PR (with static activation scaling):
qps = 1: 9.8 ms ITL, 0.49s e2e latency
qps = 2: 9.7 ms ITL, 0.49s e2e latency
qps = 4: 10.2 ms ITL, 0.53s e2e latency
qps = 6: 11.9 ms ITL, 0.59s e2e latency
qps = 8: 11.9 ms ITL, 0.59s e2e latency
qps = 10: 12.1 ms ITL, 0.61s e2e latency
2024-05-01 11:47:38 -07:00
Kunshang Ji
f4bc4de1b1
[Core]refactor aqlm quant ops ( #4351 )
2024-04-25 15:03:56 -04:00
James Fleming
2b7949c1c2
AQLM CUDA support ( #3287 )
...
Co-authored-by: mgoin <michael@neuralmagic.com>
2024-04-23 13:59:33 -04:00
Kunshang Ji
e9da5a40c6
[Misc] Add indirection layer for custom ops ( #3913 )
2024-04-10 20:26:07 -07:00
Adrian Abeyta
2ff767b513
Enable scaled FP8 (e4m3fn) KV cache on ROCm (AMD GPU) ( #3290 )
...
Co-authored-by: Gregory Shtrasberg <Gregory.Shtrasberg@amd.com>
Co-authored-by: HaiShaw <hixiao@gmail.com>
Co-authored-by: AdrianAbeyta <Adrian.Abeyta@amd.com>
Co-authored-by: Matthew Wong <Matthew.Wong2@amd.com>
Co-authored-by: root <root@gt-pla-u18-08.pla.dcgpu>
Co-authored-by: mawong-amd <156021403+mawong-amd@users.noreply.github.com>
Co-authored-by: ttbachyinsda <ttbachyinsda@outlook.com>
Co-authored-by: guofangze <guofangze@kuaishou.com>
Co-authored-by: Michael Goin <mgoin64@gmail.com>
Co-authored-by: jacobthebanana <50071502+jacobthebanana@users.noreply.github.com>
Co-authored-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
2024-04-03 14:15:55 -07:00
SangBin Cho
01bfb22b41
[CI] Try introducing isort. ( #3495 )
2024-03-25 07:59:47 -07:00
youkaichao
8fe8386591
[Kernel] change benchmark script so that result can be directly used; tune moe kernel in A100/H100 with tp=2,4,8 ( #3389 )
2024-03-14 08:11:48 +00:00
Terry
7e9bd08f60
Add batched RoPE kernel ( #3095 )
2024-03-13 13:45:26 -07:00
Philipp Moritz
cfc15a1031
Optimize Triton MoE Kernel ( #2979 )
...
Co-authored-by: Cade Daniel <edacih@gmail.com>
2024-02-26 13:48:56 -08:00
Kunshang Ji
96b6f475dd
Remove hardcoded device="cuda" to support more devices ( #2503 )
...
Co-authored-by: Jiang Li <jiang1.li@intel.com>
Co-authored-by: Kunshang Ji <kunshang.ji@intel.com>
2024-02-01 15:46:39 -08:00
zhaoyang-star
9090bf02e7
Support FP8-E5M2 KV Cache ( #2279 )
...
Co-authored-by: zhaoyang <zhao.yang16@zte.com.cn>
Co-authored-by: Zhuohan Li <zhuohan123@gmail.com>
2024-01-28 16:43:54 -08:00
wbn
dacaf5a400
Replace head_mapping params with num_kv_heads to attention kernel. ( #1997 )
...
Co-authored-by: wangguoya <wangguoya@baidu.com>
Co-authored-by: Yang Zhao <zhaoyangstar@foxmail.com>
2023-12-10 10:12:53 -08:00
Yanming W
e0c6f556e8
[Build] Avoid building too many extensions ( #1624 )
2023-11-23 16:31:19 -08:00
Woosuk Kwon
928de46888
Implement PagedAttention V2 ( #1348 )
2023-10-16 00:59:57 -07:00
