[PR #1017] [CLOSED] my nsys commands #10435

Closed
opened 2026-04-12 23:00:34 -05:00 by GiteaMirror · 0 comments
Owner

📋 Pull Request Information

Original PR: https://github.com/ollama/ollama/pull/1017
Author: @jmikedupont2
Created: 11/6/2023
Status: Closed

Base: mainHead: feature/nsys


📝 Commits (10+)

📊 Changes

117 files changed (+644754 additions, -0 deletions)

View changed files

cuobjdump.org (+53 -0)
cuobjdump.ptx.txt (+117452 -0)
cuobjdump.py (+12 -0)
names/_Z10k_get_rowsILi1ELi1EXadL_ZN43_INTERNAL_25a57f3b_12_ggml_cuda_cu_2317e5a611convert_f16EPKviiR6float2EEfEvS2_PKiPT2_i.txt (+59 -0)
names/_Z10k_get_rowsILi1ELi1EXadL_ZN43_INTERNAL_25a57f3b_12_ggml_cuda_cu_2317e5a611convert_f32EPKviiR6float2EEfEvS2_PKiPT2_i.txt (+50 -0)
names/_Z10k_get_rowsILi32ELi1EXadL_ZN43_INTERNAL_25a57f3b_12_ggml_cuda_cu_2317e5a615dequantize_q8_0EPKviiR6float2EEfEvS2_PKiPT2_i.txt (+73 -0)
names/_Z10k_get_rowsILi32ELi2EXadL_ZN43_INTERNAL_25a57f3b_12_ggml_cuda_cu_2317e5a615dequantize_q4_0EPKviiR6float2EEfEvS2_PKiPT2_i.txt (+79 -0)
names/_Z10k_get_rowsILi32ELi2EXadL_ZN43_INTERNAL_25a57f3b_12_ggml_cuda_cu_2317e5a615dequantize_q4_1EPKviiR6float2EEfEvS2_PKiPT2_i.txt (+91 -0)
names/_Z10k_get_rowsILi32ELi2EXadL_ZN43_INTERNAL_25a57f3b_12_ggml_cuda_cu_2317e5a615dequantize_q5_0EPKviiR6float2EEfEvS2_PKiPT2_i.txt (+96 -0)
names/_Z10k_get_rowsILi32ELi2EXadL_ZN43_INTERNAL_25a57f3b_12_ggml_cuda_cu_2317e5a615dequantize_q5_1EPKviiR6float2EEfEvS2_PKiPT2_i.txt (+108 -0)
names/_Z11cpy_f32_f16IXadL_ZN43_INTERNAL_25a57f3b_12_ggml_cuda_cu_2317e5a613cpy_1_f32_f16EPKcPcEEEvS2_S3_iiiiiiiiiii.txt (+80 -0)
names/_Z11cpy_f32_f16IXadL_ZN43_INTERNAL_25a57f3b_12_ggml_cuda_cu_2317e5a613cpy_1_f32_f32EPKcPcEEEvS2_S3_iiiiiiiiiii.txt (+75 -0)
names/_Z12mul_mat_q2_KILb0EEvPKvS1_Pfiiiii.txt (+6072 -0)
names/_Z12mul_mat_q2_KILb1EEvPKvS1_Pfiiiii.txt (+6280 -0)
names/_Z12mul_mat_q3_KILb0EEvPKvS1_Pfiiiii.txt (+32963 -0)
names/_Z12mul_mat_q3_KILb1EEvPKvS1_Pfiiiii.txt (+33218 -0)
names/_Z12mul_mat_q4_0ILb0EEvPKvS1_Pfiiiii.txt (+7233 -0)
names/_Z12mul_mat_q4_0ILb1EEvPKvS1_Pfiiiii.txt (+7416 -0)
names/_Z12mul_mat_q4_1ILb0EEvPKvS1_Pfiiiii.txt (+8802 -0)
names/_Z12mul_mat_q4_1ILb1EEvPKvS1_Pfiiiii.txt (+8985 -0)

...and 80 more files

📄 Description

Start of using nsys on ollama


🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.

## 📋 Pull Request Information **Original PR:** https://github.com/ollama/ollama/pull/1017 **Author:** [@jmikedupont2](https://github.com/jmikedupont2) **Created:** 11/6/2023 **Status:** ❌ Closed **Base:** `main` ← **Head:** `feature/nsys` --- ### 📝 Commits (10+) - [`b5799ac`](https://github.com/ollama/ollama/commit/b5799ac2a3744fa70ea411ebc7eac1f75367e261) my nsys commands - [`9305566`](https://github.com/ollama/ollama/commit/930556651c6528047d5fd6a0d2336fdab93c0fd5) first self eval - [`f7195fd`](https://github.com/ollama/ollama/commit/f7195fd72be5415cf680922ccba17ead479ad15c) formatting for web - [`dabc433`](https://github.com/ollama/ollama/commit/dabc4332da9d17ba3217496cedba688e4f316a3e) more formatting - [`f6257d4`](https://github.com/ollama/ollama/commit/f6257d40e2f298dd7c459a9fec494a7ee3eb9bcb) fighting with org mode - [`e8b514f`](https://github.com/ollama/ollama/commit/e8b514fdc680e86face0166e5854db4582e1232e) update - [`426202c`](https://github.com/ollama/ollama/commit/426202c3e9ee357430d33844bdd95391aa42f0c6) update formatting - [`28fe3e5`](https://github.com/ollama/ollama/commit/28fe3e5822793cc25b17231ddc38014c11ff95d5) adding list of sqlite tables - [`f022eb7`](https://github.com/ollama/ollama/commit/f022eb7d4ee5a95f265974183b21fcc8a312e635) update table sorted - [`9bd3e5e`](https://github.com/ollama/ollama/commit/9bd3e5e2f9cd457fe16417706c35113780e578a7) adding sample ### 📊 Changes **117 files changed** (+644754 additions, -0 deletions) <details> <summary>View changed files</summary> ➕ `cuobjdump.org` (+53 -0) ➕ `cuobjdump.ptx.txt` (+117452 -0) ➕ `cuobjdump.py` (+12 -0) ➕ `names/_Z10k_get_rowsILi1ELi1EXadL_ZN43_INTERNAL_25a57f3b_12_ggml_cuda_cu_2317e5a611convert_f16EPKviiR6float2EEfEvS2_PKiPT2_i.txt` (+59 -0) ➕ `names/_Z10k_get_rowsILi1ELi1EXadL_ZN43_INTERNAL_25a57f3b_12_ggml_cuda_cu_2317e5a611convert_f32EPKviiR6float2EEfEvS2_PKiPT2_i.txt` (+50 -0) ➕ `names/_Z10k_get_rowsILi32ELi1EXadL_ZN43_INTERNAL_25a57f3b_12_ggml_cuda_cu_2317e5a615dequantize_q8_0EPKviiR6float2EEfEvS2_PKiPT2_i.txt` (+73 -0) ➕ `names/_Z10k_get_rowsILi32ELi2EXadL_ZN43_INTERNAL_25a57f3b_12_ggml_cuda_cu_2317e5a615dequantize_q4_0EPKviiR6float2EEfEvS2_PKiPT2_i.txt` (+79 -0) ➕ `names/_Z10k_get_rowsILi32ELi2EXadL_ZN43_INTERNAL_25a57f3b_12_ggml_cuda_cu_2317e5a615dequantize_q4_1EPKviiR6float2EEfEvS2_PKiPT2_i.txt` (+91 -0) ➕ `names/_Z10k_get_rowsILi32ELi2EXadL_ZN43_INTERNAL_25a57f3b_12_ggml_cuda_cu_2317e5a615dequantize_q5_0EPKviiR6float2EEfEvS2_PKiPT2_i.txt` (+96 -0) ➕ `names/_Z10k_get_rowsILi32ELi2EXadL_ZN43_INTERNAL_25a57f3b_12_ggml_cuda_cu_2317e5a615dequantize_q5_1EPKviiR6float2EEfEvS2_PKiPT2_i.txt` (+108 -0) ➕ `names/_Z11cpy_f32_f16IXadL_ZN43_INTERNAL_25a57f3b_12_ggml_cuda_cu_2317e5a613cpy_1_f32_f16EPKcPcEEEvS2_S3_iiiiiiiiiii.txt` (+80 -0) ➕ `names/_Z11cpy_f32_f16IXadL_ZN43_INTERNAL_25a57f3b_12_ggml_cuda_cu_2317e5a613cpy_1_f32_f32EPKcPcEEEvS2_S3_iiiiiiiiiii.txt` (+75 -0) ➕ `names/_Z12mul_mat_q2_KILb0EEvPKvS1_Pfiiiii.txt` (+6072 -0) ➕ `names/_Z12mul_mat_q2_KILb1EEvPKvS1_Pfiiiii.txt` (+6280 -0) ➕ `names/_Z12mul_mat_q3_KILb0EEvPKvS1_Pfiiiii.txt` (+32963 -0) ➕ `names/_Z12mul_mat_q3_KILb1EEvPKvS1_Pfiiiii.txt` (+33218 -0) ➕ `names/_Z12mul_mat_q4_0ILb0EEvPKvS1_Pfiiiii.txt` (+7233 -0) ➕ `names/_Z12mul_mat_q4_0ILb1EEvPKvS1_Pfiiiii.txt` (+7416 -0) ➕ `names/_Z12mul_mat_q4_1ILb0EEvPKvS1_Pfiiiii.txt` (+8802 -0) ➕ `names/_Z12mul_mat_q4_1ILb1EEvPKvS1_Pfiiiii.txt` (+8985 -0) _...and 80 more files_ </details> ### 📄 Description Start of using nsys on ollama --- <sub>🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.</sub>
GiteaMirror added the pull-request label 2026-04-12 23:00:34 -05:00
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#10435