From a874c02b9034101a538dc11ae08da0b768bffe71 Mon Sep 17 00:00:00 2001 From: Alvaro Bartolome <36760800+alvarobartt@users.noreply.github.com> Date: Tue, 7 Jan 2025 09:54:43 +0100 Subject: [PATCH 1/2] Fix `mountPath` to use `/tmp` instead of `/data` --- .../llm-multiple-gpus/falcon-40b/text-generation-inference.yaml | 2 +- .../llm-multiple-gpus/llama2-70b/text-generation-inference.yaml | 2 +- .../llm-multiple-gpus/llama3-70b/text-generation-inference.yaml | 2 +- .../mixtral-8x7b/text-generation-inference.yaml | 2 +- 4 files changed, 4 insertions(+), 4 deletions(-) diff --git a/ai-ml/llm-multiple-gpus/falcon-40b/text-generation-inference.yaml b/ai-ml/llm-multiple-gpus/falcon-40b/text-generation-inference.yaml index 107eb36309..46d8226237 100644 --- a/ai-ml/llm-multiple-gpus/falcon-40b/text-generation-inference.yaml +++ b/ai-ml/llm-multiple-gpus/falcon-40b/text-generation-inference.yaml @@ -51,7 +51,7 @@ spec: volumeMounts: - mountPath: /dev/shm name: dshm - - mountPath: /data + - mountPath: /tmp name: ephemeral-volume volumes: - name: dshm diff --git a/ai-ml/llm-multiple-gpus/llama2-70b/text-generation-inference.yaml b/ai-ml/llm-multiple-gpus/llama2-70b/text-generation-inference.yaml index 541f353e59..d41f732b17 100644 --- a/ai-ml/llm-multiple-gpus/llama2-70b/text-generation-inference.yaml +++ b/ai-ml/llm-multiple-gpus/llama2-70b/text-generation-inference.yaml @@ -56,7 +56,7 @@ spec: volumeMounts: - mountPath: /dev/shm name: dshm - - mountPath: /data + - mountPath: /tmp name: ephemeral-volume volumes: - name: dshm diff --git a/ai-ml/llm-multiple-gpus/llama3-70b/text-generation-inference.yaml b/ai-ml/llm-multiple-gpus/llama3-70b/text-generation-inference.yaml index e34e297f6a..c96b4aa695 100644 --- a/ai-ml/llm-multiple-gpus/llama3-70b/text-generation-inference.yaml +++ b/ai-ml/llm-multiple-gpus/llama3-70b/text-generation-inference.yaml @@ -58,7 +58,7 @@ spec: volumeMounts: - mountPath: /dev/shm name: dshm - - mountPath: /data + - mountPath: /tmp name: ephemeral-volume volumes: - name: dshm diff --git a/ai-ml/llm-multiple-gpus/mixtral-8x7b/text-generation-inference.yaml b/ai-ml/llm-multiple-gpus/mixtral-8x7b/text-generation-inference.yaml index ba7c229a8c..16813a4ce9 100644 --- a/ai-ml/llm-multiple-gpus/mixtral-8x7b/text-generation-inference.yaml +++ b/ai-ml/llm-multiple-gpus/mixtral-8x7b/text-generation-inference.yaml @@ -56,7 +56,7 @@ spec: volumeMounts: - mountPath: /dev/shm name: dshm - - mountPath: /data + - mountPath: /tmp name: ephemeral-volume volumes: - name: dshm From af62d0ca6f6e1d16ad81006c57583c9d8025774b Mon Sep 17 00:00:00 2001 From: Alvaro Bartolome <36760800+alvarobartt@users.noreply.github.com> Date: Wed, 8 Jan 2025 09:06:52 +0100 Subject: [PATCH 2/2] Add comment on `mountPath` for `ephemeral-volume` set to `/tmp` --- .../falcon-40b/text-generation-inference.yaml | 3 +++ .../llama2-70b/text-generation-inference.yaml | 3 +++ .../llama3-70b/text-generation-inference.yaml | 3 +++ .../mixtral-8x7b/text-generation-inference.yaml | 3 +++ 4 files changed, 12 insertions(+) diff --git a/ai-ml/llm-multiple-gpus/falcon-40b/text-generation-inference.yaml b/ai-ml/llm-multiple-gpus/falcon-40b/text-generation-inference.yaml index 46d8226237..91ea07f11b 100644 --- a/ai-ml/llm-multiple-gpus/falcon-40b/text-generation-inference.yaml +++ b/ai-ml/llm-multiple-gpus/falcon-40b/text-generation-inference.yaml @@ -51,6 +51,9 @@ spec: volumeMounts: - mountPath: /dev/shm name: dshm + # mountPath is set to /tmp as it's the path where the HF_HOME environment + # variable points to i.e. where the downloaded model from the Hub will be + # stored - mountPath: /tmp name: ephemeral-volume volumes: diff --git a/ai-ml/llm-multiple-gpus/llama2-70b/text-generation-inference.yaml b/ai-ml/llm-multiple-gpus/llama2-70b/text-generation-inference.yaml index d41f732b17..fed7d27c80 100644 --- a/ai-ml/llm-multiple-gpus/llama2-70b/text-generation-inference.yaml +++ b/ai-ml/llm-multiple-gpus/llama2-70b/text-generation-inference.yaml @@ -56,6 +56,9 @@ spec: volumeMounts: - mountPath: /dev/shm name: dshm + # mountPath is set to /tmp as it's the path where the HF_HOME environment + # variable points to i.e. where the downloaded model from the Hub will be + # stored - mountPath: /tmp name: ephemeral-volume volumes: diff --git a/ai-ml/llm-multiple-gpus/llama3-70b/text-generation-inference.yaml b/ai-ml/llm-multiple-gpus/llama3-70b/text-generation-inference.yaml index c96b4aa695..6c4ebe8ed5 100644 --- a/ai-ml/llm-multiple-gpus/llama3-70b/text-generation-inference.yaml +++ b/ai-ml/llm-multiple-gpus/llama3-70b/text-generation-inference.yaml @@ -58,6 +58,9 @@ spec: volumeMounts: - mountPath: /dev/shm name: dshm + # mountPath is set to /tmp as it's the path where the HF_HOME environment + # variable points to i.e. where the downloaded model from the Hub will be + # stored - mountPath: /tmp name: ephemeral-volume volumes: diff --git a/ai-ml/llm-multiple-gpus/mixtral-8x7b/text-generation-inference.yaml b/ai-ml/llm-multiple-gpus/mixtral-8x7b/text-generation-inference.yaml index 16813a4ce9..4ea097a73f 100644 --- a/ai-ml/llm-multiple-gpus/mixtral-8x7b/text-generation-inference.yaml +++ b/ai-ml/llm-multiple-gpus/mixtral-8x7b/text-generation-inference.yaml @@ -56,6 +56,9 @@ spec: volumeMounts: - mountPath: /dev/shm name: dshm + # mountPath is set to /tmp as it's the path where the HF_HOME environment + # variable points to i.e. where the downloaded model from the Hub will be + # stored - mountPath: /tmp name: ephemeral-volume volumes: