Disable Cachix pushes (#3312)

* Disable Cachix pushes

This is not safe until we have sandboxed builds. For TGI alone
this might not be a huge issue, but with Cachix caching disabled
in hf-nix, TGI CI would build all the packages and push it to
our cache.

* fix: bump docs

---------

Co-authored-by: drbh <david.richard.holtz@gmail.com>

.github/workflows/nix_build.yaml

@@ -23,7 +23,7 @@ jobs:
       with:
         name: huggingface
         # If you chose signing key for write access
-        authToken: '${{ secrets.CACHIX_AUTH_TOKEN }}'
+        # authToken: '${{ secrets.CACHIX_AUTH_TOKEN }}'
       env:
         USER: github_runner
     - name: Build

.github/workflows/nix_cache.yaml

@@ -22,7 +22,7 @@ jobs:
         with:
           name: huggingface
           # If you chose signing key for write access
-          authToken: "${{ secrets.CACHIX_AUTH_TOKEN }}"
+          #authToken: "${{ secrets.CACHIX_AUTH_TOKEN }}"
         env:
           USER: github_runner
       - name: Build impure devshell

.github/workflows/nix_tests.yaml

@@ -27,9 +27,11 @@ jobs:
       with:
         name: huggingface
         # If you chose signing key for write access
-        authToken: '${{ secrets.CACHIX_AUTH_TOKEN }}'
+        #authToken: '${{ secrets.CACHIX_AUTH_TOKEN }}'
       env:
         USER: github_runner
+    - name: Nix info
+      run: nix-shell -p nix-info --run "nix-info -m"
     - name: Build
       run: nix develop .#test --command echo "Ok"
     - name: Pre-commit tests.

docs/source/reference/launcher.md

@@ -59,8 +59,6 @@ Options:
           
           Marlin kernels will be used automatically for GPTQ/AWQ models.
 
-          [env: QUANTIZE=]
-
           Possible values:
           - awq:                4 bit quantization. Requires a specific AWQ quantized model: <https://hf.co/models?search=awq>. Should replace GPTQ models wherever possible because of the better latency
           - compressed-tensors: Compressed tensors, which can be a mixture of different quantization methods
@@ -73,6 +71,8 @@ Options:
           - bitsandbytes-fp4:   Bitsandbytes 4bit. nf4 should be preferred in most cases but maybe this one has better perplexity performance for you model
           - fp8:                [FP8](https://developer.nvidia.com/blog/nvidia-arm-and-intel-publish-fp8-specification-for-standardization-as-an-interchange-format-for-ai/) (e4m3) works on H100 and above This dtype has native ops should be the fastest if available. This is currently not the fastest because of local unpacking + padding to satisfy matrix multiplication limitations
           
+          [env: QUANTIZE=]
+
 ```
 ## SPECULATE
 ```shell
@@ -457,14 +457,14 @@ Options:
       --usage-stats <USAGE_STATS>
           Control if anonymous usage stats are collected. Options are "on", "off" and "no-stack" Defaul is on
 
-          [env: USAGE_STATS=]
-          [default: on]
-
           Possible values:
           - on:       Default option, usage statistics are collected anonymously
           - off:      Disables all collection of usage statistics
           - no-stack: Doesn't send the error stack trace or error type, but allows sending a crash event
           
+          [env: USAGE_STATS=]
+          [default: on]
+
 ```
 ## PAYLOAD_LIMIT
 ```shell