iHore/vLLM
8
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity
6,768 Commits 3 Branches 0 Tags
6881107948c00a8564bc2fa85308f6fc2f065d64
Commit Graph
79 Commits
Author SHA1 Message Date
Gregory Shtrasberg 0c15c2e486 [Bugfix] config.head_dim is now explicitly set to None (#18432) 
Signed-off-by: Gregory Shtrasberg <Gregory.Shtrasberg@amd.com>
 2025-05-20 21:04:33 -07:00
Isotr0py f07a673eb2 [Misc] Allow AutoWeightsLoader to skip loading weights with specific substr in name (#18358) 
Signed-off-by: Isotr0py <2037008807@qq.com>
 2025-05-19 20:20:12 -07:00
Harry Mellor 26d0419309 Update deprecated type hinting in models (#18132) 
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
 2025-05-14 22:06:50 -07:00
Woosuk Kwon b411418ff0 [Chore] Remove Sampler from Model Code (#17084) 
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
 2025-04-24 02:49:33 -07:00
Aaron Ang a564797151 [Model] use AutoWeightsLoader for granite, granitemoe, granitemoeshared, grok1, mixtral (#16325) 
Signed-off-by: Aaron Ang <aaron.angyd@gmail.com>
 2025-04-09 20:07:40 -07:00
Quentin aaaec52ad9 [Bugfix][Model] Mixtral: use unused head_dim config argument (#14961) 
Signed-off-by: Quentin Torroba <quentin.torroba@mistral.ai>
 2025-03-17 07:44:18 -07:00
Tyler Michael Smith 72c62eae5f [V1] EP/TP MoE + DP Attention (#13931) 2025-03-04 21:27:26 -08:00
Tyler Michael Smith 4f5b059f14 Clean up unused padding_idx variables across many model definitions (#13240) 
Signed-off-by: Tyler Michael Smith <tyler@neuralmagic.com>
 2025-03-04 21:27:00 +00:00
Harry Mellor cdc1fa12eb Remove unused kwargs from model definitions (#13555) 2025-02-24 17:13:52 -08:00
Jee Jee Li 105b8ce4c0 [Misc] Reduce LoRA-related static variable (#13166) 2025-02-22 00:21:30 -08:00
Russell Bryant e489ad7a21 [Misc] Add SPDX-License-Identifier headers to python source files (#12628) 
- **Add SPDX license headers to python source files**
- **Check for SPDX headers using pre-commit**

commit 9d7ef44c3cfb72ca4c32e1c677d99259d10d4745
Author: Russell Bryant <rbryant@redhat.com>
Date:   Fri Jan 31 14:18:24 2025 -0500

    Add SPDX license headers to python source files
    
This commit adds SPDX license headers to python source files as
recommended to
the project by the Linux Foundation. These headers provide a concise way
that is
both human and machine readable for communicating license information
for each
source file. It helps avoid any ambiguity about the license of the code
and can
    also be easily used by tools to help manage license compliance.
    
The Linux Foundation runs license scans against the codebase to help
ensure
    we are in compliance with the licenses of the code we use, including
dependencies. Having these headers in place helps that tool do its job.
    
    More information can be found on the SPDX site:
    
    - https://spdx.dev/learn/handling-license-info/
    
    Signed-off-by: Russell Bryant <rbryant@redhat.com>

commit 5a1cf1cb3b80759131c73f6a9dddebccac039dea
Author: Russell Bryant <rbryant@redhat.com>
Date:   Fri Jan 31 14:36:32 2025 -0500

    Check for SPDX headers using pre-commit
    
    Signed-off-by: Russell Bryant <rbryant@redhat.com>

---------

Signed-off-by: Russell Bryant <rbryant@redhat.com>
 2025-02-02 11:58:18 -08:00
Pavani Majetyandmgoin b02fd288b2 [Hardware][NV] Fix Modelopt model loading for k-v-scales for Llama models. (#11787) 
Signed-off-by: Pavani Majety <pmajety@nvidia.com>
Co-authored-by: mgoin <michael@neuralmagic.com>
 2025-01-29 01:46:12 -08:00
Michael Goin 9aa1519f08 Various cosmetic/comment fixes (#12089) 
Signed-off-by: mgoin <michael@neuralmagic.com>
 2025-01-16 09:59:06 +00:00
kewang-xlnxkewang2Michael Goin
 		de0526f668 [Misc][Quark] Upstream Quark format to VLLM (#10765) 
Signed-off-by: kewang-xlnx <kewang@xilinx.com>
Signed-off-by: kewang2 <kewang2@amd.com>
Co-authored-by: kewang2 <kewang2@amd.com>
Co-authored-by: Michael Goin <michael@neuralmagic.com>
 2025-01-15 11:05:15 -05:00
youkaichao eebad39f26 [torch.compile] support all attention backends (#10558) 
Signed-off-by: youkaichao <youkaichao@gmail.com>
 2024-11-22 14:04:42 -08:00
Isotr0py c4e464333e [Misc] Add uninitialized params tracking for AutoWeightsLoader (#10327) 
Signed-off-by: Isotr0py <2037008807@qq.com>
 2024-11-18 09:07:46 +08:00
Roger Wang 643ecf7b11 [V1] Refactor model executable interface for all text-only language models (#10374) 
Signed-off-by: Roger Wang <ywang@roblox.com>
 2024-11-17 05:18:46 +00:00
youkaichao f89d18ff74 [6/N] pass whole config to inner model (#10205) 
Signed-off-by: youkaichao <youkaichao@gmail.com>
 2024-11-11 06:41:46 +00:00
youkaichao 1a95f10ee7 [5/N] pass the whole config to model (#9983) 
Signed-off-by: youkaichao <youkaichao@gmail.com>
 2024-11-09 14:17:28 +08:00
Joe Runde d58268c56a [V1] Make v1 more testable (#9888) 
Signed-off-by: Joe Runde <Joseph.Runde@ibm.com>
 2024-11-06 11:57:35 -08:00
Aaron Pham 21063c11c7 [CI/Build] drop support for Python 3.8 EOL (#8464) 
Signed-off-by: Aaron Pham <contact@aarnphm.xyz>
 2024-11-06 07:11:55 +00:00
Yongzao aa0addb397 Adding "torch compile" annotations to moe models (#9758) 2024-10-28 13:49:56 -07:00
Prashant Gupta 9ade8bbc8d [Model] add a bunch of supported lora modules for mixtral (#9008) 
Signed-off-by: Prashant Gupta <prashantgupta@us.ibm.com>
 2024-10-04 16:24:40 +00:00
Murali AndoorveeduandDarkLight1337 0f6d7a9a34 [Models] Add remaining model PP support (#7168) 
Signed-off-by: Muralidhar Andoorveedu <muralidhar.andoorveedu@centml.ai>
Signed-off-by: Murali Andoorveedu <muralidhar.andoorveedu@centml.ai>
Co-authored-by: DarkLight1337 <tlleungac@connect.ust.hk>
 2024-10-04 10:56:58 +08:00
Dipika Sikka 6cd5e5b07e [Misc] Fused MoE Marlin support for GPTQ (#8217) 2024-09-09 23:02:52 -04:00
afeldman-nm 428dd1445e [Core] Logprobs support in Multi-step (#7652) 2024-08-29 19:19:08 -07:00
Dipika SikkaandElizaWszola fc911880cc [Kernel] Expand MoE weight loading + Add Fused Marlin MoE Kernel (#7766) 
Co-authored-by: ElizaWszola <eliza@neuralmagic.com>
 2024-08-27 15:07:09 -07:00
Michael Goin aae74ef95c Revert "[Kernel] Expand MoE weight loading + Add Fused Marlin MoE Kernel (#7527)" (#7764) 2024-08-22 03:42:14 +00:00
Dipika SikkaandElizaWszola 8678a69ab5 [Kernel] Expand MoE weight loading + Add Fused Marlin MoE Kernel (#7527) 
Co-authored-by: ElizaWszola <eliza@neuralmagic.com>
 2024-08-21 16:17:10 -07:00
Zijian Hu f4fc7337bf [Bugfix] support tie_word_embeddings for all models (#5724) 2024-08-19 20:00:04 -07:00
Dipika Sikka d3bdfd3ab9 [Misc] Update Fused MoE weight loading (#7334) 2024-08-13 14:57:45 -04:00
Cyrus Leung 7025b11d94 [Bugfix] Fix weight loading for Chameleon when TP>1 (#7410) 2024-08-13 05:33:41 +00:00
Robert Shaw dbe5588554 [ Misc ] non-uniform quantization via compressed-tensors for Llama (#6515) 2024-07-18 22:39:18 -04:00
Cody Yu b5af8c223c [Model] Pipeline parallel support for Mixtral (#6516) 2024-07-17 19:26:04 -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 fb6af8bc08 [ Misc ] Apply MoE Refactor to Deepseekv2 To Support Fp8 (#6417) 2024-07-13 20:03:58 -07:00
Woosuk Kwon e72ae80b06 [Bugfix] Support 2D input shape in MoE layer (#6287) 2024-07-10 09:03:16 -04:00
Qubitium-ModelCloudRobert ShawZX
 		ee93f4f92a [CORE] Quantized lm-head Framework (#4442) 
Co-authored-by: Robert Shaw <rshaw@neuralmagic.com>
Co-authored-by: ZX <zx@lbx.dev>
 2024-07-02 22:25:17 +00:00
Robert ShawRobert ShawMichael Goin
 		7c008c51a9 [ Misc ] Refactor MoE to isolate Fp8 From Mixtral (#5970) 
Co-authored-by: Robert Shaw <rshaw@neuralmagic>
Co-authored-by: Michael Goin <michael@neuralmagic.com>
 2024-07-02 21:54:35 +00:00
Murali Andoorveedu c5832d2ae9 [Core] Pipeline Parallel Support (#4412) 
Signed-off-by: Muralidhar Andoorveedu <muralidhar.andoorveedu@centml.ai>
 2024-07-02 10:58:08 -07:00
Cyrus Leung 98cf2ed678 [Model][Bugfix] Implicit model flags and reenable Phi-3-Vision (#5896) 2024-06-27 09:08:10 -07:00
Cyrus Leung 96354d6a29 [Model] Add base class for LoRA-supported models (#5018) 2024-06-27 16:03:04 +08:00
Michael Goin c09dade2a2 [Misc][Breaking] Change FP8 checkpoint format from act_scale -> input_scale (#5353) 2024-06-08 13:54:05 -04:00
Cody Yu 5563a4dea8 [Model] Correct Mixtral FP8 checkpoint loading (#5231) 2024-06-05 10:58:50 -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
Zhuohan Lirsnm2Robert Shaw
 		1102bef219 [Bugfix / Core] Prefix Caching Guards (merged with main) (#4846) 
Co-authored-by: rsnm2 <rshaw@neuralmagic.com>
Co-authored-by: Robert Shaw <114415538+robertgshaw2-neuralmagic@users.noreply.github.com>
 2024-05-27 15:18:17 -07:00
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
Philipp Moritz 33d3914b1e [Bugfix] Fix dynamic FP8 quantization for Mixtral (#4793) 2024-05-13 19:00:27 -04:00
Woosuk Kwon 0fca3cdcf2 [Misc] Enhance attention selector (#4751) 2024-05-13 10:47:25 -07:00
Michael Goin 2a052011ca [Kernel] Support MoE Fp8 Checkpoints for Mixtral (Static Weights with Dynamic/Static Activations) (#4527) 
Follow on to #4332 to enable FP8 checkpoint loading for Mixtral and supersedes #4436.

This PR enables the following checkpoint loading features for Mixtral:

Supports loading fp8 checkpoints for Mixtral, such as this "nm-testing/Mixtral-8x7B-Instruct-v0.1-FP8" test model
Supports static or dynamic activation quantization with static weight quantization (all per tensor)
Supports different scales for each expert weight
Supports Fp8 in QKV layer
Notes:

The Expert Gate/Router always runs at half / full precision for now.
If there are different weight scales between QKV layer (for separate QKV weights), they are re-quantized using layer.weight_scale.max() so we can have a single gemm for performance.
 2024-05-04 11:45:16 -07:00