Fix

Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>

Author: DarkLight1337

.pre-commit-config.yaml

@@ -33,9 +33,11 @@ repos:
   rev: v0.9.27
   hooks:
   - id: pymarkdown
-    # NOTE: If you get an AssertionError when applying fixes,
-    # try setting args to [scan] and fix the lint errors manually
-    args: [fix]
+    # Conflicts with pyml disable, so we flag this to be fixed manually
+    args: [fix, -d, md007]
+  hooks:
+  - id: pymarkdown
+    args: [scan]
 - repo: https://github.com/rhysd/actionlint
   rev: v1.7.7
   hooks:

csrc/quantization/machete/Readme.md

@@ -6,25 +6,25 @@ Machete is a spiritual successor to the Marlin kernel but optimized for Hopper a
 
 Machete effectively performs
 
-```
+```python
 scale_type = w_s.dtype
 compute_type = a.dtype
 out = (w_q.to(scale_type) * w_s - w_z.to(scale_type)) @ a
 ```
 
-Where `w_q` is a quantized weight matrix, `w_s` is the quantization scales, and 
+Where `w_q` is a quantized weight matrix, `w_s` is the quantization scales, and
 `w_z` is the quantization zeropoints.
 
-> **_NOTE:_**  `w_z` is added after the scales so we can 
+> **_NOTE:_**  `w_z` is added after the scales so we can
 use FMA operations, but this means they must have the scales pre-applied if the
-supplied zeropoints assume that they will be subtracted before the scales are 
+supplied zeropoints assume that they will be subtracted before the scales are
 applied.
 
 ## API
 
 The main optimization within Machete is prepacking the weight matrix to more closely match the tensor core layouts, allowing for wider shared memory loads when loading the weight matrix. This means that the weight matrix must be prepacked before calling `machete_gemm`. The flow looks something like:
 
-```
+```python
 from vllm import _custom_ops as ops
 
 ...
@@ -40,6 +40,6 @@ output = ops.machete_gemm(
 
 ## Code Generation
 
-Since Machete is based on Cutlass, we can generate multiple type pairs and different tile shapes using the same kernel template. We generate multiple instantiations of this template using `generate.py`. 
+Since Machete is based on Cutlass, we can generate multiple type pairs and different tile shapes using the same kernel template. We generate multiple instantiations of this template using `generate.py`.
 
-New type pairs (`TypeConfig`s) can be appended to `impl_configs` (in `generate()`), and these will get automatically generated (assuming they can be supported without issues). For each `TypeConfig`, you must also provide an `ImplConfig`, which bundles a `TypeConfig` with a list of `ScheduleConfig`s, `Specialization`s, and a default heuristic. The `ScheduleConfig`s (which contain info on tile shapes, tile scheduler, etc.) can perform differently for different problem shapes, and there is almost never one `ScheduleConfig` that works well for all problem shapes, so it is generally beneficial to generate different `ScheduleConfig`s for different potential problem shapes. This is where the heuristic comes in. For each `TypeConfig`, a default heuristic should be provided. This maps different problem shapes to different `ScheduleConfig`s and is used when the user does not provide the `schedule` parameter to `machete_gemm`. The `Specialization`s define what feature combinations to generate, i.e., `with_zeropoints`, `with_scales`, etc. We can reduce compile times and the final binary size by limiting the set of feature combinations we generate.
+New type pairs (`TypeConfig`s) can be appended to `impl_configs` (in `generate()`), and these will get automatically generated (assuming they can be supported without issues). For each `TypeConfig`, you must also provide an `ImplConfig`, which bundles a `TypeConfig` with a list of `ScheduleConfig`s, `Specialization`s, and a default heuristic. The `ScheduleConfig`s (which contain info on tile shapes, tile scheduler, etc.) can perform differently for different problem shapes, and there is almost never one `ScheduleConfig` that works well for all problem shapes, so it is generally beneficial to generate different `ScheduleConfig`s for different potential problem shapes. This is where the heuristic comes in. For each `TypeConfig`, a default heuristic should be provided. This maps different problem shapes to different `ScheduleConfig`s and is used when the user does not provide the `schedule` parameter to `machete_gemm`. The `Specialization`s define what feature combinations to generate, i.e., `with_zeropoints`, `with_scales`, etc. We can reduce compile times and the final binary size by limiting the set of feature combinations we generate.

docs/source/serving/engine_args.md

@@ -4,7 +4,7 @@
 
 Below, you can find an explanation of every engine argument for vLLM:
 
-<!--- pyml disable-num-lines 7 no-space-in-emphasis-->
+<!--- pyml disable-num-lines 7 no-space-in-emphasis -->
 ```{eval-rst}
 .. argparse::
     :module: vllm.engine.arg_utils
@@ -17,7 +17,7 @@ Below, you can find an explanation of every engine argument for vLLM:
 
 Below are the additional arguments related to the asynchronous engine:
 
-<!--- pyml disable-num-lines 7 no-space-in-emphasis-->
+<!--- pyml disable-num-lines 7 no-space-in-emphasis -->
 ```{eval-rst}
 .. argparse::
     :module: vllm.engine.arg_utils

examples/offline_inference/openai/openai_batch.md

@@ -182,7 +182,7 @@ aws s3 cp s3://MY_BUCKET/MY_OUTPUT_FILE.jsonl -
 
 Add embedding requests to your batch file. The following is an example:
 
-```jsonl
+```text
 {"custom_id": "request-1", "method": "POST", "url": "/v1/embeddings", "body": {"model": "intfloat/e5-mistral-7b-instruct", "input": "You are a helpful assistant."}}
 {"custom_id": "request-2", "method": "POST", "url": "/v1/embeddings", "body": {"model": "intfloat/e5-mistral-7b-instruct", "input": "You are an unhelpful assistant."}}
 ```
@@ -213,7 +213,7 @@ $ cat results.jsonl
 
 Add score requests to your batch file. The following is an example:
 
-```jsonl
+```text
 {"custom_id": "request-1", "method": "POST", "url": "/v1/score", "body": {"model": "BAAI/bge-reranker-v2-m3", "text_1": "What is the capital of France?", "text_2": ["The capital of Brazil is Brasilia.", "The capital of France is Paris."]}}
 {"custom_id": "request-2", "method": "POST", "url": "/v1/score", "body": {"model": "BAAI/bge-reranker-v2-m3", "text_1": "What is the capital of France?", "text_2": ["The capital of Brazil is Brasilia.", "The capital of France is Paris."]}}
 ```