Enable Dynamic MoE for Mixtral on 1.19.0 (#425)

Move Dynamic MoE implementation to habana_main. It was previously
implemented for 1.18, but had to be modified as ops have been moved to
[github.com/HabanaAI/vllm-hpu-extension](https://github.com/HabanaAI/vllm-hpu-extension).
Works with bf16, uses static (legacy) mode when running with
quantization.

Related PRs:
- #303
- HabanaAI/vllm-hpu-extension#13

---

<details>
<!-- inside this <details> section, markdown rendering does not work, so
we use raw html here. -->
<summary><b> PR Checklist (Click to Expand) </b></summary>

<p>Thank you for your contribution to vLLM! Before submitting the pull
request, please ensure the PR meets the following criteria. This helps
vLLM maintain the code quality and improve the efficiency of the review
process.</p>

<h3>PR Title and Classification</h3>
<p>Only specific types of PRs will be reviewed. The PR title is prefixed
appropriately to indicate the type of change. Please use one of the
following:</p>
<ul>
    <li><code>[Bugfix]</code> for bug fixes.</li>
<li><code>[CI/Build]</code> for build or continuous integration
improvements.</li>
<li><code>[Doc]</code> for documentation fixes and improvements.</li>
<li><code>[Model]</code> for adding a new model or improving an existing
model. Model name should appear in the title.</li>
<li><code>[Frontend]</code> For changes on the vLLM frontend (e.g.,
OpenAI API server, <code>LLM</code> class, etc.) </li>
<li><code>[Kernel]</code> for changes affecting CUDA kernels or other
compute kernels.</li>
<li><code>[Core]</code> for changes in the core vLLM logic (e.g.,
<code>LLMEngine</code>, <code>AsyncLLMEngine</code>,
<code>Scheduler</code>, etc.)</li>
<li><code>[Hardware][Vendor]</code> for hardware-specific changes.
Vendor name should appear in the prefix (e.g.,
<code>[Hardware][AMD]</code>).</li>
<li><code>[Misc]</code> for PRs that do not fit the above categories.
Please use this sparingly.</li>
</ul>
<p><strong>Note:</strong> If the PR spans more than one category, please
include all relevant prefixes.</p>

<h3>Code Quality</h3>

<p>The PR need to meet the following code quality standards:</p>

<ul>
<li>We adhere to <a
href="https://google.github.io/styleguide/pyguide.html">Google Python
style guide</a> and <a
href="https://google.github.io/styleguide/cppguide.html">Google C++
style guide</a>.</li>
<li>Pass all linter checks. Please use <a
href="https://github.com/vllm-project/vllm/blob/main/format.sh"><code>format.sh</code></a>
to format your code.</li>
<li>The code need to be well-documented to ensure future contributors
can easily understand the code.</li>
<li>Include sufficient tests to ensure the project to stay correct and
robust. This includes both unit tests and integration tests.</li>
<li>Please add documentation to <code>docs/source/</code> if the PR
modifies the user-facing behaviors of vLLM. It helps vLLM user
understand and utilize the new features or changes.</li>
</ul>

<h3>Adding or changing kernels</h3>
<p>Each custom kernel needs a schema and one or more implementations to
be registered with PyTorch.</p>
<ul>
<li>Make sure custom ops are registered following PyTorch guidelines: <a
href="https://pytorch.org/tutorials/advanced/cpp_custom_ops.html#cpp-custom-ops-tutorial">Custom
C++ and CUDA Operators</a> and <a
href="https://docs.google.com/document/d/1_W62p8WJOQQUzPsJYa7s701JXt0qf2OfLub2sbkHOaU">The
Custom Operators Manual</a></li>
<li>Custom operations that return <code>Tensors</code> require
meta-functions. Meta-functions should be implemented and registered in
python so that dynamic dims can be handled automatically. See above
documents for a description of meta-functions.</li>
<li>Use <a
href="https://pytorch.org/docs/stable/library.html#torch.library.opcheck"><code>torch.libary.opcheck()</code></a>
to test the function registration and meta-function for any registered
ops. See <code>tests/kernels</code> for examples.</li>
<li>When changing the C++ signature of an existing op, the schema must
be updated to reflect the changes.</li>
<li>If a new custom type is needed, see the following document: <a
href="https://docs.google.com/document/d/18fBMPuOJ0fY5ZQ6YyrHUppw9FA332CpNtgB6SOIgyuA">Custom
Class Support in PT2</a>.
</ul>

<h3>Notes for Large Changes</h3>
<p>Please keep the changes as concise as possible. For major
architectural changes (>500 LOC excluding kernel/data/config/test), we
would expect a GitHub issue (RFC) discussing the technical design and
justification. Otherwise, we will tag it with <code>rfc-required</code>
and might not go through the PR.</p>

<h3>What to Expect for the Reviews</h3>

<p>The goal of the vLLM team is to be a <i>transparent reviewing
machine</i>. We would like to make the review process transparent and
efficient and make sure no contributor feel confused or frustrated.
However, the vLLM team is small, so we need to prioritize some PRs over
others. Here is what you can expect from the review process: </p>

<ul>
<li> After the PR is submitted, the PR will be assigned to a reviewer.
Every reviewer will pick up the PRs based on their expertise and
availability.</li>
<li> After the PR is assigned, the reviewer will provide status update
every 2-3 days. If the PR is not reviewed within 7 days, please feel
free to ping the reviewer or the vLLM team.</li>
<li> After the review, the reviewer will put an <code>
action-required</code> label on the PR if there are changes required.
The contributor should address the comments and ping the reviewer to
re-review the PR.</li>
<li> Please respond to all comments within a reasonable time frame. If a
comment isn't clear or you disagree with a suggestion, feel free to ask
for clarification or discuss the suggestion.
 </li>
</ul>

<h3>Thank You</h3>

<p> Finally, thank you for taking the time to read these guidelines and
for your interest in contributing to vLLM. Your contributions make vLLM
a great tool for everyone! </p>


</details>

requirements-hpu.txt

@@ -8,4 +8,4 @@ pandas
 tabulate
 setuptools>=61
 setuptools-scm>=8
-vllm-hpu-extension @ git+https://github.com/HabanaAI/vllm-hpu-extension.git@341a77f
+vllm-hpu-extension @ git+https://github.com/HabanaAI/vllm-hpu-extension.git@341a77f

vllm/model_executor/layers/fused_moe/layer.py

@@ -226,9 +226,13 @@ def __init__(
         self.num_expert_group = num_expert_group
         self.topk_group = topk_group
         self.custom_routing_function = custom_routing_function
-        if current_platform.is_hpu():
-            from vllm_hpu_extension.ops import StaticFusedMOE
-            self.hpu_static_fused_moe = StaticFusedMOE(self.num_experts)
+        if is_hpu:
+            from vllm_hpu_extension.ops import DynamicFusedMOE, StaticFusedMOE
+
+            from vllm.model_executor.layers.quantization.inc import INCConfig
+            selected_fused_moe = (StaticFusedMOE if isinstance(
+                quant_config, INCConfig) else DynamicFusedMOE)
+            self.hpu_static_fused_moe = selected_fused_moe(self.num_experts)
 
         if quant_config is None:
             self.quant_method: Optional[QuantizeMethodBase] = (
@@ -321,8 +325,10 @@ def _load_w13(self,
         expert_data.copy_(loaded_weight)
 
         if is_hpu:
-            self.hpu_static_fused_moe.w13_list[expert_id].set_weight(
-                orig_exp_data)
+            from vllm_hpu_extension.ops import StaticFusedMOE
+            if isinstance(self.hpu_static_fused_moe, StaticFusedMOE):
+                self.hpu_static_fused_moe.w13_list[expert_id].set_weight(
+                    orig_exp_data)
 
     def _load_w2(self,
                  expert_data: torch.Tensor,
@@ -341,8 +347,10 @@ def _load_w2(self,
         # w2, down_proj: Load into only logical weight of w2.
         expert_data.copy_(loaded_weight)
         if is_hpu:
-            self.hpu_static_fused_moe.w2_list[expert_id].set_weight(
-                expert_data)
+            from vllm_hpu_extension.ops import StaticFusedMOE
+            if isinstance(self.hpu_static_fused_moe, StaticFusedMOE):
+                self.hpu_static_fused_moe.w2_list[expert_id].set_weight(
+                    expert_data)
 
     def _load_single_value(self, param: torch.nn.Parameter,
                            loaded_weight: torch.Tensor, expert_id: int):