GitLab

Signed-off-by: Divakar Verma <divakar.verma@amd.com>

Signed-off-by: Divakar Verma <divakar.verma@amd.com>

Signed-off-by: Roger Wang <ywang@roblox.com>
Co-authored-by: Xiaoyu Zhang <BBuf@users.noreply.github.com>

Signed-off-by: ElizaWszola <eliza@neuralmagic.com>

Signed-off-by: Lucas Wilkinson <lwilkinson@neuralmagic.com>

Signed-off-by: Aaron Pham <contact@aarnphm.xyz>

Signed-off-by: wangshuai09 <391746016@qq.com>

Signed-off-by: youkaichao <youkaichao@gmail.com>

Co-authored-by: mgoin <michael@neuralmagic.com>
Co-authored-by: Divakar Verma <137818590+divakar-amd@users.noreply.github.com>
Co-authored-by: Tyler Michael Smith <tyler@neuralmagic.com>

Signed-off-by: Aaron Pham <contact@aarnphm.xyz>
Co-authored-by: Cyrus Leung <cyrus.tl.leung@gmail.com>

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

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

Co-authored-by: Zhuohan Li <zhuohan123@gmail.com>

The 2nd PR for #4532.

This PR supports loading FP8 kv-cache scaling factors from a FP8 checkpoint (with .kv_scale parameter).

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

Co-authored-by: mgoin <michael@neuralmagic.com>

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>

[Kernel] change benchmark script so that result can be directly used; tune moe kernel in A100/H100 with tp=2,4,8 (#3389)