[Doc]: Updating GitHub link (#5)

* updating github link

* Changing project references

* minor change

* should_use_given_dir flag from prefill_profiler

README.md

@@ -20,7 +20,7 @@ Tool to benchmark LLM Inference Systems
 
 ### Clone repository
 ```bash
-git clone https://github.com/gatech-sysml/metron.git
+git clone https://github.com/project-metron/metron.git
 ```
 
 ### Create conda environment

docs/index.rst

@@ -40,5 +40,5 @@ If you use our work, please consider citing our paper:
 
 Acknowledgement
 ---------------
-`metron <https://github.com/gatech-sysml/metron>`_ code was originally created as a fork from `LLMPerf <https://github.com/ray-project/llmperf>`_ project.
+`metron <https://github.com/project-metron/metron>`_ code was originally created as a fork from `LLMPerf <https://github.com/ray-project/llmperf>`_ project.
 

docs/installation.rst

@@ -9,7 +9,7 @@ Clone Repository
 
 .. code-block:: shell
 
-    git clone https://github.com/gatech-sysml/metron.git
+    git clone https://github.com/project-metron/metron.git
 
 Create Conda Environment
 ~~~~~~~~~~~~~~~~~~~~~~~~

docs/tutorials/prefill_profiler.rst

@@ -21,8 +21,7 @@ And, then run the following command:
     --timeout 600 \
     --num-concurrent-requests 1 \
     --fixed-request-generator-decode-tokens 16 \
-    --output-dir "prefill_experiments/prefill_profiler_vllm_llama-3-8b" \
-    --should-use-given-dir true
+    --output-dir "prefill_experiments/prefill_profiler_vllm_llama-3-8b"
 
 Adjusting Prompt Lengths
 ~~~~~~~~~~~~~~~~~~~~~~~~
@@ -44,6 +43,5 @@ To profile a custom range of prompt lengths, use the flag ``--prefill-lengths``
     --num-concurrent-requests 1 \
     --fixed-request-generator-decode-tokens 16 \
     --output-dir "prefill_experiments/prefill_profiler_vllm_llama-3-8b" \
-    --should-use-given-dir true \
     --prefill-lengths 256 512 1024 2048 4096 8192 16384 32768 65536