vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

ggml : SOTA 2-bit quants (add IQ2_XS) (#4856)

Browse source 
* iq2_xs: basics

* iq2_xs: this should have been in the basics

* iq2_xs: CUDA and scalar CPU works

* iq2_xs: WIP Metal

* iq2_xs: Metal now works

* iq2_xs: working, but dog slow, ARM_NEON dot product

* iq2_xs: better ARM_NEON dot product

We are now at 19.5 t/s for TG-128 and 61 t/s for PP-512 when
running on the CPU.

* iq2_xs: AVX2 dot product - 19.5 t/s

* iq2_xs: faster AVX2 dit product

21.4 t/s for TG-128, 59.2 t/s for PP-512.
The latter is 2x compared to the previous version.

* iq2_xs: had forgotten to delete iq2-data.h

* Add llama enum for IQ2_XS

---------

Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
This commit is contained in:
Kawrakow 2024-01-11 20:39:39 +01:00 • committed by GitHub
parent 3ba5b8ca8e
commit 49662cbed3
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
10 changed files with 1038 additions and 28 deletions
Download patch file Download diff file Expand all files Collapse all files

12
ggml-quants.h
View file

@ -174,6 +174,14 @@ typedef struct {
} block_iq2_xxs;
static_assert(sizeof(block_iq2_xxs) == sizeof(ggml_fp16_t) + QK_K/8*sizeof(uint16_t), "wrong iq2_xxs block size/padding");
// 2.3125 bpw quants
typedef struct {
ggml_fp16_t d;
uint16_t qs[QK_K/8];
uint8_t scales[QK_K/32];
} block_iq2_xs;
static_assert(sizeof(block_iq2_xs) == sizeof(ggml_fp16_t) + QK_K/8*sizeof(uint16_t) + QK_K/32, "wrong iq2_xs block size/padding");
// Quantization
void quantize_row_q4_0_reference(const float * restrict x, block_q4_0 * restrict y, int k);
void quantize_row_q4_1_reference(const float * restrict x, block_q4_1 * restrict y, int k);
@ -189,6 +197,7 @@ void quantize_row_q5_K_reference(const float * restrict x, block_q5_K * restrict
void quantize_row_q6_K_reference(const float * restrict x, block_q6_K * restrict y, int k);
void quantize_row_q8_K_reference(const float * restrict x, block_q8_K * restrict y, int k);
void quantize_row_iq2_xxs_reference(const float * restrict x, block_iq2_xxs * restrict y, int k);
void quantize_row_iq2_xs_reference (const float * restrict x, block_iq2_xs * restrict y, int k);
void quantize_row_q4_0(const float * restrict x, void * restrict y, int k);
void quantize_row_q4_1(const float * restrict x, void * restrict y, int k);
@ -204,6 +213,7 @@ void quantize_row_q5_K(const float * restrict x, void * restrict y, int k);
void quantize_row_q6_K(const float * restrict x, void * restrict y, int k);
void quantize_row_q8_K(const float * restrict x, void * restrict y, int k);
void quantize_row_iq2_xxs(const float * restrict x, void * restrict y, int k);
void quantize_row_iq2_xs (const float * restrict x, void * restrict y, int k);
// Dequantization
void dequantize_row_q4_0(const block_q4_0 * restrict x, float * restrict y, int k);
@ -220,6 +230,7 @@ void dequantize_row_q5_K(const block_q5_K * restrict x, float * restrict y, int
void dequantize_row_q6_K(const block_q6_K * restrict x, float * restrict y, int k);
void dequantize_row_q8_K(const block_q8_K * restrict x, float * restrict y, int k);
void dequantize_row_iq2_xxs(const block_iq2_xxs * restrict x, float * restrict y, int k);
void dequantize_row_iq2_xs (const block_iq2_xs * restrict x, float * restrict y, int k);
// Dot product
void ggml_vec_dot_q4_0_q8_0(int n, float * restrict s, const void * restrict vx, const void * restrict vy);
@ -234,3 +245,4 @@ void ggml_vec_dot_q4_K_q8_K(int n, float * restrict s, const void * restrict vx,
void ggml_vec_dot_q5_K_q8_K(int n, float * restrict s, const void * restrict vx, const void * restrict vy);
void ggml_vec_dot_q6_K_q8_K(int n, float * restrict s, const void * restrict vx, const void * restrict vy);
void ggml_vec_dot_iq2_xxs_q8_K(int n, float * restrict s, const void * restrict vx, const void * restrict vy);
void ggml_vec_dot_iq2_xs_q8_K (int n, float * restrict s, const void * restrict vx, const void * restrict vy);